System

Abstract

To provide a system that streamlines a selection of new business partners and a preparation of proposal contents, and optimizes a result of the streamlining.SOLUTION: A system includes the means of: preparing a domestic corporate list; listing up attribute corporates having the same attribute as an excellent customer from the domestic corporate list, and making a recommendation, using a generative AI model; comparing pieces of past data on the excellent customer and the attribute corporate using the generative AI model, and thereby simulating suggestion and improvement in a customer performance based on the suggestion; and generating a draft policy and suggestion on the basis of a result of the simulation, using the generative AI model.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] The selection of potential new business partners and the creation of proposals to those business partners rely heavily on human experience and intuition, which may not always produce optimal results, and the process is time-consuming, labor-intensive, and inefficient. [Means for solving the problem]

[0005] The present invention uses AI to compile a list of companies with the same attributes as good customers from a list of companies in Japan, and recommends them as candidates for new business partners. Furthermore, the AI ​​compares them with good customers and simulates what proposals would improve the customer's performance. Then, based on the results, the AI ​​generates a proposal policy and a proposal document. This makes the selection of new business partners and the creation of proposal content more efficient, and optimizes the results. [Brief description of the drawings]

[0006] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 2 is a sequence diagram showing a process flow of the data processing system in the first embodiment of the first form example. [Figure 12] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the application example 1 of the first embodiment. [Figure 13] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the second embodiment of the second embodiment. [Figure 14] FIG. 13 is a sequence diagram showing a process flow of the data processing system in application example 2 of embodiment 2. [Figure 15] FIG. 13 is a sequence diagram showing a process flow of a data processing system in a third embodiment of the present invention. [Figure 16] FIG. 13 is a sequence diagram showing a process flow of the data processing system in the third application example of the third embodiment. [Figure 17] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when combined with an emotion engine. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0008] First, the terms used in the following description will be explained.

[0009] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0011] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0012] In the following embodiments, the communication I / F (Interface) with the code is a communication processor and

[0013] The communication I / F is an interface including a power supply, a power source, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0014] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0015] [First embodiment]

[0016] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (e.g., voice and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Fig. 2, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific process program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0026] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores a reception output program 60. The reception output program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads out the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0027] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0028] "Example 1"

[0029] One embodiment of the present invention is a system for developing new business partners using AI. This system creates a list of companies in Japan, and from that list, makes a list of companies that have similar attributes to good customers. The AI ​​performs analysis to make the list, taking into consideration attributes such as the company's industry, size, and region. Next, the AI ​​compares the company with good customers and simulates what proposals would improve the customer's performance. This simulation is performed based on past transaction history and market trends. Finally, the AI ​​generates a proposal plan and a proposal document based on the results. This proposal document includes the specific proposal content, its reasons, expected effects, etc.

[0030] "Example 2"

[0031] As a specific example, if a good client is a major company in the IT industry, small and medium-sized enterprises in the same industry will be listed as potential new business partners. Then, based on what proposals the good client received in the past that improved their performance, AI will simulate whether a similar proposal would lead to improved performance for the new business partner candidate. Based on the results, AI will generate a proposal for the new business partner candidate. This proposal will include specific actions that the new business partner candidate should take, their effects, and the services we provide to support those actions.

[0032] The process flow of each embodiment will be described below.

[0033] "Example 1"

[0034] Step 1: The AI ​​creates a list of companies in the country, including attributes such as the company's industry, size, and region.

[0035] Step 2: The AI ​​creates a list of companies that have similar attributes to good customers. This list is created by selecting companies that have similar attributes to good customers from the company list.

[0036] Step 3: The AI ​​compares the customer with a good customer and simulates what proposals would improve the customer's performance. This simulation is based on past transaction history, market trends, etc.

[0037] Step 4: The AI ​​generates a proposal based on the results of the simulation. This proposal includes the specific proposal content, its rationale, and the expected effects.

[0038] "Example 2"

[0039] Step 1: If the best customer is a large company in the IT industry, the AI ​​will list small and medium-sized companies in the same industry as potential new business partners.

[0040] Step 2: Based on what proposals good customers have received in the past that have improved their performance, the AI ​​simulates whether a similar proposal would lead to improved performance for a potential new business partner.

[0041] Step 3: Based on the results of the simulation, the AI ​​generates a proposal for the potential new business partner. This proposal describes the specific actions that the potential new business partner should take, their effects, and the services we provide to support those actions.

[0042] Example 1

[0043] Next, a description will be given of Example 1 of the embodiment 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal".

[0044] In conventional systems for developing new business partners, creating company lists, listing companies with similar attributes to good customers, simulating proposal content, and generating proposal documents are often done manually, which can be problematic in terms of efficiency. In addition, the accuracy and effectiveness of the proposal content is uncertain, and it may not lead to an improvement in customer performance. This has created a demand for more efficient sales activities and more effective proposals.

[0045] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0046] In this invention, the server includes a means for creating a list of companies in Japan, a means for listing companies with similar attributes to good customers and using AI to recommend them, a means for comparing with good customers and using AI to simulate what proposals would improve customer performance, a means for AI to generate proposal guidelines and proposals based on the simulation results, and a means for generating proposals in natural language using a generative AI model. This makes it possible to efficiently develop new business partners and generate effective proposal content.

[0047] A "domestic company list" is a list that compiles information on companies located in Japan, including attributes such as the company's industry, size, and region.

[0048] A "good customer" is a customer with a good track record of transactions and excellent performance in the past, and is an important business partner for a company.

[0049] "Attributes" is information that indicates characteristics of a company, such as its industry, size, and region.

[0050] "AI recommendation" means using artificial intelligence to recommend the most suitable companies or proposals based on specific conditions.

[0051] "Simulation" is the process of predicting results under specific conditions based on past data and market trends.

[0052] The "proposal policy" indicates the basic direction and strategy of proposals to be made to customers.

[0053] A "proposal" is a document that describes the specific proposal to be made to a customer, its reasons, expected effects, etc.

[0054] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to generate sentences based on input prompts.

[0055] "Generating in natural language" means using artificial intelligence to create sentences in natural language that humans can understand.

[0056] This invention relates to a system for developing new business partners using AI. This system creates a list of companies in Japan, and from that list, lists companies that have similar attributes to good customers. It then simulates what proposals should be made to the listed companies to improve their customer performance, and generates proposals based on the results.

[0057] The server first retrieves company information from a domestic company database. This database contains attributes such as company industry, size, and region. The server uses SQL queries to extract the necessary data and create a company list. The server then uses an AI model to list companies that have similar attributes to good customers. Data analysis libraries such as scikit-learn and Pandas are used for this analysis. The server performs clustering based on company attributes such as industry, size, and region.

[0058] The server compares the listed companies with good customers and simulates what proposals would improve customer performance. This simulation is based on data such as past transaction history and market trends, and the AI ​​model makes predictions. Specifically, it performs regression analysis and clustering using past data.

[0059] Finally, the server generates a proposal policy and a proposal document based on the simulation results. The proposal document includes the specific proposal content, its rationale, expected effects, etc. Natural language processing (NLP) technology is used to generate the proposal document, utilizing a generative AI model.

[0060] A user instructs the system to create a list of new business partners, for example by inputting the following prompt into the generative AI model:

[0061] "Create a list of companies in your country that have similar attributes to your best customers. Then, run a simulation to see what proposals you could make to these companies to improve their performance, and generate proposals based on the results."

[0062] As a concrete example, a user instructs the system to "make a list of IT companies in Tokyo with more than 100 employees and make proposals for improving performance based on past transaction history." The server creates a list of companies based on the specified conditions and performs analysis and simulations using an AI model. Finally, a proposal is generated and provided to the user.

[0063] In this way, a system is realized in which the server, terminals, and users work together to efficiently develop new business partners.

[0064] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0065] Step 1: Create a list of companies

[0066] The server retrieves company information from a national company database. As input, a database containing company attributes such as industry, size, and region is used. The server uses SQL queries to extract the required data and create a company list. As output, a company list is generated.

[0067] Specific behavior:

[0068] The server executes a SQL query against the database:

[0069] sql SELECT FROM companies WHERE region = 'Japan';

[0070] This query retrieves company information for Japan.

[0071] Step 2: List companies with similar attributes to your best customers

[0072] The server uses an AI model to create a list of companies that have similar attributes to good customers. The list of companies and attribute information of good customers are used as input. The server performs clustering based on attributes such as the company's industry, size, and region. The list of companies is generated as output.

[0073] Specific behavior:

[0074] The server executes the following Python code to perform clustering.

[0075] python from sklearn.cluster import KMeans import pandas as pd Importing company data data = pd.read_csv('companies.csv') Running clustering kmeans = KMeans(n_clusters=5) clusters = kmeans.fit_predict(data[['industry', 'size', 'region']])

[0076] This code allows companies to be classified into clusters.

[0077] Step 3: Simulate the proposal

[0078] The server compares the listed companies with good customers and simulates what proposals would improve customer performance. As input, the server uses information on the listed companies, past transaction history, market trends, and other data. The server runs the simulation using regression analysis and predictive models. As output, it generates proposals.

[0079] Specific behavior:

[0080] The server runs the following Python code to perform the simulation:

[0081] python from sklearn.linear_model import LinearRegression Loading historical transaction data transaction_data = pd.read_csv('transactions.csv') Performing regression analysis model = LinearRegression() model.fit(transaction_data[['feature1', 'feature2']], transaction_data['performance']) Running a prediction predictions = model.predict(new_company_data[['feature1', 'feature2']])

[0082] This code predicts what proposals will be made to new business partners.

[0083] Step 4: Generate a proposal

[0084] The server generates a proposal policy and a proposal based on the simulation results. The simulation results are used as input. The server generates the proposal in natural language using a generative AI model. As output, a proposal is generated.

[0085] Specific behavior:

[0086] The server inputs the following prompt sentence into the generative AI model:

[0087] python prompt = """ Please prepare a proposal for a new business partner. Based on the information below, please include the specific proposal content, its justification, and the expected effects. Industry: IT Size: Medium Region: Tokyo Past transaction history: Yes Market trends: Growing """ response = gpt3.generate(prompt)

[0088] This code will generate a proposal.

[0089] Step 5: Submit your proposal

[0090] The user receives the generated proposal and makes a proposal to the new trading partner. As input, the generated proposal is used. As output, the proposal is provided to the new trading partner.

[0091] Specific behavior:

[0092] The user downloads the proposal generated from the system and submits it to the new business partner.

[0093] (Application example 1)

[0094] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0095] Conventional systems for developing new business partners have difficulty efficiently listing companies with similar attributes to good customers and making appropriate proposals. In addition, generating proposal content requires a lot of manual work, which is time-consuming and labor-intensive. Furthermore, the system is not user-friendly because it does not take into account use on mobile devices such as smartphones and tablets. To solve these problems, a more efficient and effective system for developing new business partners is needed.

[0096] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0097] In this invention, the server includes a means for creating a list of companies in Japan, a means for listing companies with attributes similar to those of good customers and making recommendations using AI, a means for comparing with good customers and simulating what proposals would improve customer performance, a means for generating a proposal policy and a proposal document using AI, a means for simulating proposal contents for new business partners, a means for automatically generating a proposal document using a generation AI model, and a means including an application to be installed on a smartphone or tablet. This makes it possible to efficiently and effectively develop new business partners and quickly generate proposal contents.

[0098] The "domestic company list" is a list that collects basic information about companies located in the country and stores it in a database.

[0099] A "good customer" is a customer who is deemed to be of particularly high transaction value based on past transaction history and business performance.

[0100] "Attribute companies" are companies that have specific attributes such as industry, size, or region.

[0101] "AI recommendation means" is a function that uses artificial intelligence to recommend companies based on specific conditions.

[0102] A "means of simulation" is a function that predicts future results based on past data and market trends.

[0103] The "proposal policy" indicates the basic direction and strategy of the proposal content.

[0104] A "proposal" is a document that describes the specific proposal content, its reasons, and the expected effects.

[0105] A "new business partner" is a new business partner with whom we have not had any transactions until now.

[0106] A "generative AI model" is a model that is trained using artificial intelligence to perform a specific task.

[0107] A "prompt sentence" is an instruction sentence input to a generative AI model.

[0108] An "application installed on a smartphone or tablet" is software that runs on a mobile device.

[0109] A system for implementing the present invention uses a server, a mobile device such as a smartphone or tablet, and a generative AI model. The specific configuration and operation of the system are described below.

[0110] System Configuration

[0111] 1. Server

[0112] The server creates a list of companies in Japan and stores it in a database. The server also runs an AI model to analyze the attributes of good customers and list companies with similar attributes. In addition, the server simulates proposals to new clients and automatically generates proposals using a generative AI model.

[0113] 2. Mobile Devices

[0114] An application that communicates with the server is installed on a mobile device such as a smartphone or tablet, and provides an interface for the user to view a list of potential business partners and to view proposals.

[0115] Data processing and calculation

[0116] 1. Creating a list of companies

[0117] The server collects information on companies in Japan and creates a database that includes attributes such as industry, size, and region. This data is managed using Pandas.

[0118] 2. Analysis of loyal customer attributes

[0119] The server analyzes the data of good customers using KMeans clustering and classifies them into specific clusters, which makes it possible to identify companies that have similar attributes to good customers.

[0120] 3. Listing new business partners

[0121] The server filters companies that have similar attributes to its best customers and creates a list of new business partners, which is then provided to the user through an application on their mobile device.

[0122] 4. Proposed Simulation

[0123] The server uses RandomForestRegressor to simulate proposals for new trading partners. This simulation is based on past trading history and market trends.

[0124] 5. Proposal Generation

[0125] The server uses the generative AI model to automatically generate a proposal. This proposal includes the specific proposal content, its rationale, and the expected effects. The generative AI model uses the OpenAI (registered trademark) API.

[0126] Examples

[0127] For example, for manufacturing company A, we generate the following prompt:

[0128] Company name: Company A Industry: Manufacturing Scale: 100 Region: Tokyo

[0129] Generate a proposal.

[0130] When this prompt sentence is input into the generative AI model, the AI ​​generates a specific proposal. For example, it may return a proposal such as, "The introduction of a new manufacturing line is expected to improve efficiency by 20%." In this way, users can make effective proposals to new business partners.

[0131] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0132] Step 1:

[0133] The server collects company information in the country and creates a database with attributes such as industry, size, region, etc. As input, it requires a data source of company information (e.g., a public company database) and as output, it obtains a list of companies in the form of a Pandas data frame. This data is used for subsequent analysis.

[0134] Step 2:

[0135] The server analyzes the data of good customers using KMeans clustering and classifies them into specific clusters. As input, it requires data of good customers (e.g. past transaction history, performance data), and as output, it obtains data of good customers with cluster labels. These cluster labels are used to identify the attributes of good customers.

[0136] Step 3:

[0137] The server filters companies with similar attributes to good customers and creates a list of new business partners. As input, it requires data of good customers with cluster labels and a list of companies in the country, and as output, it obtains a list of new business partners. This list is provided to the user through an application on the mobile device.

[0138] Step 4:

[0139] The server uses RandomForestRegressor to simulate proposals for new trading partners. As input, it requires a list of new trading partners and data on past trading history and market trends. As output, it obtains predictions of proposal contents. These predictions are used to generate proposal documents.

[0140] Step 5:

[0141] The server uses the generative AI model to automatically generate proposals. The inputs required are the predicted results of the proposal content and basic information about the new business partner (e.g. company name, industry, size, region), and the output is a proposal that includes the specific proposal content, its justification, and the expected effects. The generative AI model uses the OpenAI API.

[0142] Step 6:

[0143] A user views a list of new business partners and proposals through an application installed on a smartphone or tablet. As input, a list of new business partners and proposals provided by a server are required, and as output, they are displayed in a format that can be viewed by the user. This application provides an interface for the user to make effective proposals to new business partners.

[0144] Example 2

[0145] Next, a second embodiment of the second embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0146] With the conventional system, it was difficult to make specific proposals to potential new business partners based on the success stories of good customers. In addition, it took a lot of time and effort to generate proposals, which made it difficult to conduct efficient sales activities.

[0147] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for creating a list of domestic companies, a means for listing companies with the same attributes as good customers and making recommendations using artificial intelligence, a means for comparing with good customers and simulating using artificial intelligence what proposals would improve customer performance, a means for generating a proposal based on the simulation results, and a means for providing the generated proposal to the user. This makes it possible to efficiently make specific proposals based on the success stories of good customers.

[0148] The "Domestic Company List" is a list that compiles information on companies located in Japan.

[0149] A "good customer" is a customer who has a good track record of transactions in the past and who can be expected to continue doing business with the company.

[0150] "Attribute companies" are companies that share a particular industry, size, or other common characteristics.

[0151] "Artificial intelligence" is a technology that enables computer systems to imitate human intelligence to learn and make inferences.

[0152] A "recommendation" is the suggestion of the best option based on specific criteria.

[0153] "Simulation" refers to the virtual reproduction of a real-world situation and predicting its outcomes.

[0154] A "proposal" is a document that documents a specific proposal and indicates specific actions to a business partner.

[0155] A "user" is someone who uses this system to create proposals and make them to business partners.

[0156] The present invention is a system for efficiently making specific proposals to potential new business partners based on success stories of good customers. A specific embodiment of this system will be described below.

[0157] The server first creates a list of companies in Japan. To do this, a database management system (e.g., MySQL (registered trademark)) is used to collect information on companies located in the country. Next, data on good customers is collected and past transaction records and performance data are analyzed. This analysis is performed using Python's Pandas library and NumPy library.

[0158] The server refers to an industry database to list companies with similar attributes to good customers. This allows small and medium-sized enterprises in the same industry to be extracted as potential new business partners. The extracted company list is recommended using artificial intelligence (e.g., generative AI model).

[0159] Next, the server simulates whether a proposal for a potential new business partner will lead to improved business performance based on the success stories of good customers. This simulation uses a generative AI model (e.g., GPT-4 (registered trademark)). Specific examples of prompt sentences include the following:

[0160] "Our good customer A has improved its performance in the past after receiving the following proposal. Please simulate what kind of effect you can expect if we make a similar proposal to a potential new business partner B."

[0161] Based on the simulation results, the server generates a proposal for the potential new business partner. This proposal describes the specific actions that the potential new business partner should take, their effects, and the services to support those actions. The generative AI model is used again to generate the proposal. Examples of specific prompt sentences include the following:

[0162] "Please prepare a proposal for potential new business partner B. In the proposal, please describe the specific actions that B should take, their effects, and the services we can provide to support those actions."

[0163] The generated proposal is provided to the user via the terminal. The user can make specific proposals to potential new business partners based on this proposal. This makes it possible to efficiently make specific proposals based on the success stories of good customers.

[0164] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0165] Step 1: Data collection

[0166] The server collects company information using a database management system (e.g., MySQL) to create a list of companies in Japan. As input, it obtains basic information about the companies (e.g., company name, location, industry, and size). As output, it generates a list of companies in Japan. Specifically, the server executes SQL queries to extract the required information from the database.

[0167] Step 2: Analyze your loyal customer data

[0168] The server collects and analyzes past transaction data and performance data of good customers. As input, it obtains transaction history and performance data of good customers. As output, it identifies successful proposals and factors that improved performance. Specifically, the server uses Python's Pandas library to analyze the data and extract success stories.

[0169] Step 3: List potential new business partners

[0170] The server refers to an industry database to list companies that have similar attributes as good customers. As input, it retrieves company information from the industry database. As output, it generates a list of potential new business partners. Specifically, the server executes an SQL query to extract companies that match the criteria.

[0171] Step 4: Simulation

[0172] The server simulates whether proposals for potential new business partners will lead to improved business performance, based on success stories of good customers. As input, it inputs the success stories of good customers and information on potential new business partners into the generative AI model. As output, it obtains the simulation results. In concrete terms, the server inputs the following prompt sentence into the generative AI model (e.g. GPT-4):

[0173] "Our good customer A has improved its performance in the past after receiving the following proposal. Please simulate what kind of effect you can expect if we make a similar proposal to a potential new business partner B."

[0174] Step 5: Generate a proposal

[0175] The server generates a proposal for a potential new business partner based on the simulation results. As input, it inputs the simulation results and information on the potential new business partner into the generative AI model. As output, a proposal is generated. Specifically, the server inputs the following prompt sentence into the generative AI model:

[0176] "Please prepare a proposal for potential new business partner B. In the proposal, please describe the specific actions that B should take, their effects, and the services we can provide to support those actions."

[0177] Step 6: Submit your proposal

[0178] The server sends the generated proposal to the terminal. As input, the server obtains the generated proposal. As output, the proposal is provided to the user. As a specific operation, the server sends the proposal to the terminal, and the terminal displays the proposal so that the user can confirm it. The user can make a specific proposal to a potential new business partner based on this proposal.

[0179] (Application example 2)

[0180] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0181] With conventional systems, it was difficult to make effective proposals to potential new business partners based on the success stories of good customers. In addition, there was a problem that efficient sales activities could not be carried out because it took a lot of time and effort to generate proposals. Furthermore, the content of the proposals sometimes lacked consistency, which could reduce the trust of potential new business partners. In order to solve these issues, there is a need for a system that can generate prompt sentences based on the success stories of good customers and automatically generate effective proposals using AI.

[0182] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0183] In this invention, the server includes a means for creating a list of companies in Japan, a means for listing companies with attributes similar to those of good customers and making recommendations using AI, a means for comparing with good customers and simulating what proposals would improve customer performance, a means for AI to generate a proposal policy and a proposal, a means for generating a prompt sentence based on success stories of good customers, a means for generating a proposal based on the generated prompt sentence, and a means for outputting a proposal for a new business partner candidate. This makes it possible to automatically generate effective proposals based on success stories of good customers quickly and consistently.

[0184] A "means for creating a domestic company list" is a method or device for collecting information on companies existing in the country and organizing it in list form.

[0185] "Means for compiling a list of companies with similar attributes to good customers and recommending them using AI" refers to a method or device for identifying companies that have similar characteristics to good customers and recommending these companies using artificial intelligence.

[0186] "A means of using AI to simulate what proposals will improve customer performance by comparing with good customers" refers to a method or device that compares data on good customers with data on potential new business partners and uses artificial intelligence to predict what kind of proposals will contribute to improving performance.

[0187] "Means for AI-generated proposal guidelines and written proposals" refers to methods or devices for automatically creating proposal guidelines and specific written proposals using artificial intelligence.

[0188] "Means for generating prompt sentences based on success stories of good customers" refers to a method or device for creating instruction sentences (prompt sentences) for artificial intelligence based on past success stories of good customers.

[0189] The "means for generating a proposal based on the generated prompt sentence" refers to a method or device for an artificial intelligence to automatically create a proposal using the generated prompt sentence as input.

[0190] The "means for outputting a proposal to a new supplier candidate" refers to a method or device for presenting the generated proposal to the new supplier candidate.

[0191] An embodiment of the present invention will now be described. First, the system uses the following hardware and software.

[0192] Hardware and Software Used

[0193] Hardware: Servers, smartphones

[0194] Software: Python, OpenAI API, Pandas

[0195] System Configuration

[0196] The server includes the following means:

[0197] 1. Means for creating a list of domestic companies: The server collects information on companies existing in the country and organizes it in the form of a list. This list includes basic information, business performance data, industry, etc. of the companies.

[0198] 2. Compiling a list of companies with similar attributes to those of best customers and using AI to recommend them: The server identifies companies with similar characteristics based on data on best customers and uses artificial intelligence to recommend these companies.

[0199] 3. A means of using AI to simulate what proposals would improve customer performance by comparing with best customers: The server compares data on best customers with data on potential new business partners, and uses artificial intelligence to predict what kind of proposals would contribute to improving performance.

[0200] 4. Means for AI to generate proposal guidelines and written proposals: The server uses artificial intelligence to automatically create proposal guidelines and specific written proposals.

[0201] 5. Means for generating prompt sentences based on success stories of good customers: The server creates instructions (prompt sentences) for the artificial intelligence based on past success stories of good customers.

[0202] 6. Means for generating a proposal based on the generated prompt sentence: The server uses the generated prompt sentence as input and the artificial intelligence automatically creates a proposal.

[0203] 7. Means for outputting a proposal to a potential new business partner: The server presents the generated proposal to the potential new business partner.

[0204] Data processing and calculation

[0205] The server collects data on good customers and potential new business partners, compares and analyzes this data, and uses Python and Pandas to read the data and OpenAI API to perform simulations and generate proposals using artificial intelligence.

[0206] Examples

[0207] For example, if a good customer is a "major IT company" that has been successful in the past when "SEO optimization and content marketing" was proposed to them, they can use that success story to make a similar proposal to a potential new business partner, a "small and medium-sized IT company."

[0208] Examples of prompt statements A valued client (a large IT company) saw an improvement in their business performance after receiving the following recommendations: SEO optimization and content marketing. Run a simulation to see if a similar recommendation would be effective for a potential new business partner (a small or medium-sized IT company).

[0209] In this way, the server can quickly and consistently automatically generate effective proposals based on best customer success stories.

[0210] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0211] Step 1:

[0212] The server creates a list of companies in Japan. Specifically, it collects basic information, performance data, industry, etc. of companies and organizes them in list form. As input, it uses company databases and publicly available company information, and as output, it generates an organized company list.

[0213] Step 2:

[0214] The server creates a list of companies with similar attributes to good customers and uses AI to make recommendations. Specifically, it identifies companies with similar characteristics based on the data of good customers and uses artificial intelligence to recommend these companies. It uses the data of good customers and the company list as input, and generates a list of recommended companies as output.

[0215] Step 3:

[0216] The server compares the data of good customers with those of potential new business partners and uses AI to simulate what proposals would improve the customer's performance. Specifically, it compares the data of good customers with that of potential new business partners and uses artificial intelligence to predict what proposals would contribute to improving performance. The server uses the data of good customers and the data of potential new business partners as input and generates the simulation results as output.

[0217] Step 4:

[0218] The server uses AI to generate the proposal policy and proposal document. Specifically, it uses artificial intelligence to automatically create the proposal policy and specific proposal document. It uses the simulation results as input and generates the proposal policy and proposal document as output.

[0219] Step 5:

[0220] The server generates a prompt sentence based on the success stories of good customers. Specifically, it creates an instruction sentence (prompt sentence) for the artificial intelligence based on the past success stories of good customers. The success story data of good customers is used as input, and the prompt sentence is generated as output.

[0221] Step 6:

[0222] The server generates a proposal based on the generated prompt. Specifically, the AI ​​automatically creates a proposal using the generated prompt as input. The server uses the prompt as input and generates a proposal as output.

[0223] Step 7:

[0224] The server outputs a proposal to the new supplier candidate. Specifically, the server presents the generated proposal to the new supplier candidate. The server uses the generated proposal as input, and generates a proposal to be presented to the new supplier candidate as output.

[0225] Furthermore, an emotion engine that estimates the emotion of the user may be combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0226] "Example 1"

[0227] In one embodiment of the present invention, the AI ​​includes an emotion engine that recognizes the user's emotions. The emotion engine reads emotions from the user's tone of voice, facial expressions, choice of words, etc. For example, if the user is happy or excited, the emotion engine conveys that information to the AI. The AI ​​adjusts the suggestions based on that information. Specifically, if the user is happy, the AI ​​makes suggestions to amplify that happiness. Also, if the user is frustrated or angry, the AI ​​makes suggestions to resolve that frustration.

[0228] "Example 2"

[0229] In another embodiment of the present invention, the emotion engine recognizes the user's emotion and optimizes the suggestions based on the emotion. Specifically, if the user feels happy, the AI ​​makes suggestions to amplify the joy. Also, if the user feels frustrated or angry, the AI ​​makes suggestions to resolve the frustration. This optimization is achieved by learning the correlation between the user's emotion and the suggestions. For example, the AI ​​analyzes past suggestions and the user's response to learn what suggestions will amplify the user's joy and what suggestions will resolve the user's frustration.

[0230] The process flow of each embodiment will be described below.

[0231] "Example 1"

[0232] Step 1: User interaction begins, either by the user asking the system a question or by the system providing information to the user.

[0233] Step 2: The emotion engine reads the user's emotions from their tone of voice, facial expressions, choice of words, etc.

[0234] Step 3: The emotion engine communicates the emotional information it has read to the AI.

[0235] Step 4: The AI ​​adjusts the suggestions based on the emotion information. Specifically, if the user is feeling happy, the AI ​​will make suggestions to amplify that happiness. Also, if the user is feeling dissatisfied or angry, the AI ​​will make suggestions to alleviate that dissatisfaction.

[0236] "Example 2"

[0237] Step 1: User interaction begins, either by the user asking the system a question or by the system providing information to the user.

[0238] Step 2: The emotion engine reads the user's emotions from their tone of voice, facial expressions, choice of words, etc.

[0239] Step 3: The emotion engine communicates the emotional information it has read to the AI.

[0240] Step 4: The AI ​​optimizes the content of the suggestions based on the emotion information. Specifically, if the user is feeling happy, the AI ​​will make suggestions to amplify that happiness. Also, if the user is feeling dissatisfied or angry, the AI ​​will make suggestions to alleviate that dissatisfaction.

[0241] Step 5: The AI ​​analyzes past suggestions and user responses to learn which suggestions will increase user delight and which suggestions will eliminate user dissatisfaction.

[0242] Example 1

[0243] Next, a description will be given of Example 1 of the embodiment 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal".

[0244] In conventional new business partner development systems, the creation of company lists, attribute analysis of good customers, and generation of proposal content are often done manually, which is inefficient. In addition, the proposal content cannot be adjusted to take the user's feelings into account, which limits the effectiveness of the proposal. This creates the problem that companies are unable to fully improve their performance or develop new business partners.

[0245] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0246] In this invention, the server includes a means for creating a list of companies in Japan, a means for listing companies with attributes similar to those of good customers and making recommendations using artificial intelligence, a means for comparing with good customers and simulating using artificial intelligence what proposals would improve customer performance, a means for generating a proposal policy and a proposal document using artificial intelligence, and a means for adjusting the proposal contents using an emotion engine that recognizes the user's emotions. This makes it possible to efficiently create a list of companies, analyze the attributes of good customers, automatically generate proposal contents, and adjust the proposal contents according to the user's emotions.

[0247] A "domestic company list" is a list that collects information on companies that exist in Japan.

[0248] A "good customer" is a customer who has a good track record of transactions and business performance in the past.

[0249] "Attribute companies" refer to companies that are classified based on specific conditions (industry, size, region, etc.).

[0250] "Artificial intelligence" is a technology that uses machine learning and data analysis to mimic human intelligence.

[0251] A "recommendation" is the suggestion of the best option based on specific criteria.

[0252] "Simulation" refers to modeling real-world situations and conducting virtual experiments and predictions.

[0253] A "proposal" is a document that describes a specific proposal, its rationale, and the expected results.

[0254] The "emotion engine" is a technology that reads emotions from a user's tone of voice, facial expressions, choice of words, etc.

[0255] "Recommendations" refers to recommended actions or strategies for achieving a particular objective.

[0256] This invention is a system for developing new business partners using AI, which creates a list of companies in Japan and then selects from that list those with similar attributes to good customers. The system uses AI to perform analysis, taking into account attributes such as the company's industry, size, and region. Next, the AI ​​compares the company with good customers and simulates what proposals would improve the customer's performance. This simulation is performed based on past transaction history and market trends. Finally, the AI ​​generates a proposal policy and document based on the results. This proposal document includes the specific proposal content, its reasons, and expected effects.

[0257] Hardware and Software Used

[0258] Hardware: Servers, terminals

[0259] Software: AI models (e.g., TENSORFLOW®, PyTorch), emotion engines (e.g., Affectiva, Microsoft® Azure® Emotion API)

[0260] Specific operation of the system

[0261] 1. Creating a list of companies:

[0262] The server extracts company information from a national company database.

[0263] The terminal provides an interface for inputting user-specified conditions (industry type, size, region, etc.).

[0264] The user inputs the conditions through a terminal.

[0265] The server uses an AI model to filter the list of companies based on the specified criteria.

[0266] The server transmits the filtering result to the terminal.

[0267] The terminal displays the filtering results to the user.

[0268] 2. Attribute analysis of loyal customers:

[0269] The server collects data on loyal customers.

[0270] The terminal provides an interface for inputting information on preferred customers provided by the user.

[0271] The user inputs information about good customers through the terminal.

[0272] The server uses an AI model to analyze attributes of good customers, such as industry, size, and region.

[0273] Based on the analysis results, the server compiles a list of similar companies.

[0274] The server transmits the list result to the terminal.

[0275] The terminal displays the listing results to the user.

[0276] 3. Proposed simulation:

[0277] The server collects past trading history and market trend data.

[0278] The server uses an AI model to simulate what proposals would improve customer performance.

[0279] The server transmits the simulation results to the terminal.

[0280] The terminal displays the simulation results to the user.

[0281] 4. Proposal Generation:

[0282] The server decides on a proposal policy based on the simulation results.

[0283] The server uses the AI ​​model to generate a proposal that includes specific proposal details, their rationale, and expected benefits.

[0284] The server transmits the generated proposal to the terminal.

[0285] The terminal displays the proposal to the user.

[0286] 5. Using the Emotion Engine:

[0287] The device uses an emotion engine to analyze the user's tone of voice, facial expressions, choice of words, etc.

[0288] The emotion engine sends the analysis results to the server.

[0289] The server uses an AI model to tailor its suggestions based on the user's emotions.

[0290] The server sends the adjusted proposal to the terminal.

[0291] The device displays the proposed adjustments to the user.

[0292] Examples and prompts

[0293] Examples:

[0294] If a user is looking to develop new business partners, the system will list companies from a list of domestic companies based on the following criteria: industry (manufacturing), size (small and medium-sized enterprises), and region (Kanto region).

[0295] Designate "A Co., Ltd." as a valued customer and list similar companies based on its attributes.

[0296] Based on past transaction history and market trends, the system suggests "introducing product B," citing as its justification that "sales increased by 20% in past implementation cases."

[0297] When the user is reviewing the proposal, the emotion engine reads the "excitement" from the user's facial expression and further emphasizes the proposal.

[0298] Example prompt: In order to develop new business partners, please make a list of companies from a list of domestic companies with the following criteria: industry (manufacturing), size (small and medium-sized enterprises), and region (Kanto region). Specify "Corporation A" as a good customer, and make a list of similar companies based on that attribute. Based on past transaction history and market trends, simulate what proposals would improve the customer's performance, and generate a proposal that includes specific proposal content, its reasons, and the expected effects.

[0299] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0300] Step 1:

[0301] Creating a company list

[0302] Input: The user enters conditions such as industry, size, and region into the terminal.

[0303] Specific operation: The terminal receives the conditions specified by the user and sends them to the server.

[0304] Data processing: The server extracts company information that matches the specified conditions from the company database.

[0305] Output: The server generates the filtered list of companies and sends it to the terminal.

[0306] Specific operation: The terminal displays the filtering results to the user in list form.

[0307] Step 2:

[0308] Attribute analysis of loyal customers

[0309] Input: The user enters preferred customer information into the terminal.

[0310] Specific operation: The terminal receives the information on good customers provided by the user and transmits it to the server.

[0311] Data processing: The server collects data on good customers and uses an AI model to analyze attributes such as industry, size, and region.

[0312] Output: Based on the analysis results, the server creates a list of similar companies and sends it to the terminal.

[0313] Specific behavior: The terminal displays the listing results to the user.

[0314] Step 3:

[0315] Proposal Simulation

[0316] Input: The server collects historical trading and market trend data.

[0317] What happens: The server inputs this data into the AI ​​model.

[0318] Data calculation: The AI ​​model simulates what recommendations would improve customer performance.

[0319] Output: The server generates the simulation results and sends them to the terminal.

[0320] Specific operation: The terminal displays the simulation results to the user.

[0321] Step 4:

[0322] Proposal Generation

[0323] Input: The server receives the simulation results.

[0324] Specific operation: The server uses the AI ​​model to generate a proposal that includes specific proposal content, its rationale, and the expected effects.

[0325] Data processing: Format the proposal content and put it into document format.

[0326] Output: The server sends the generated proposal to the terminal.

[0327] Specific behavior: The device displays the proposal to the user.

[0328] Step 5:

[0329] Using the Emotion Engine

[0330] Input: The device collects the user's tone of voice, facial expressions, word choice, etc.

[0331] Specific operation: The device inputs the collected data into the emotion engine.

[0332] Data calculation: The emotion engine analyzes the user's emotion and sends the result to the server.

[0333] Output: The server receives the sentiment analysis results and uses the AI ​​model to refine the suggestions.

[0334] Specific operation: The server sends the adjusted proposal to the device, which then displays it to the user.

[0335] (Application example 1)

[0336] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0337] Conventional systems for developing new business partners can create company lists and generate proposals, but they do not adjust the content of the proposals to take into account the user's feelings, which means that the effectiveness of the proposals is limited. In addition, there is a lack of systems that utilize mobile devices such as smartphones, which also creates a problem of low user convenience.

[0338] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0339] In this invention, the server includes a means for creating a list of companies in Japan, a means for listing companies with attributes similar to those of good customers and making recommendations using AI, a means for comparing with good customers and simulating with AI what proposals would improve customer performance, a means for AI to generate a proposal policy and proposal, a means for adjusting the proposal content using an emotion engine that recognizes the user's emotions, and a means including an application to be installed on a smartphone. This enables effective proposals that take the user's emotions into consideration, and realizes a highly convenient system that utilizes smartphones.

[0340] The "company list" is a database that compiles domestic companies in a list format, and includes attribute information such as the company's industry, size, and region.

[0341] A "good customer" is one who is particularly valuable based on past transaction history and business performance.

[0342] "Attribute companies" refer to companies that have similar attributes, such as industry, size, and region, as good customers.

[0343] "Recommendation" means that AI performs analysis and suggests the best options based on certain conditions.

[0344] "Simulation" means that AI predicts what results a particular proposal will bring, based on past data and market trends.

[0345] A "proposal" is a document generated by AI that includes the specific proposal content, its rationale, expected effects, etc.

[0346] The "emotion engine" is a system that reads emotions from the user's tone of voice, facial expressions, choice of words, etc., and conveys that information to the AI.

[0347] A "smartphone" is a type of mobile phone, a multi-function device that can connect to the Internet and install applications.

[0348] An "application" is software installed on a smartphone that provides specific functions or services.

[0349] The following system configuration will be described as an embodiment of the present invention.

[0350] System Configuration

[0351] Hardware

[0352] Server: Manages the database, runs the AI ​​models, and processes the emotion engine.

[0353] Smartphone: Functions as a user interface and recognizes the user's emotions using a camera and microphone.

[0354] software

[0355] Database: Stores a list of companies within the country and manages data to create a list of companies with similar attributes to good customers.

[0356] AI model: A generative AI model that suggests products based on a user's purchasing history and browsing history.

[0357] Emotion engine: Software that detects emotions from a user's tone of voice, facial expressions, choice of words, etc.

[0358] Application: An application that is installed on a smartphone and allows the user to interact with it.

[0359] Data processing and calculation

[0360] server

[0361] The server first creates a list of companies in Japan, listing companies with attributes similar to those of good customers. It then uses an AI model to compare these companies with good customers and simulate what proposals would improve their performance. It also uses an emotion engine to recognize the user's emotions and adjusts the content of the proposals based on that information. Finally, it generates a proposed policy and proposal document and sends them to the smartphone.

[0362] Smartphone

[0363] The smartphone collects the user's purchase history and browsing history and sends them to the server. It also uses a camera and microphone to analyze the user's facial expressions and tone of voice and sends them to the emotion engine. The proposals received from the server are displayed to the user and an interaction takes place.

[0364] Examples

[0365] For example, when a user uses a smartphone to access an online shopping site, their purchase history and browsing history are sent to the server. Based on this data, the server uses an AI model to suggest new products. In addition, the smartphone's camera and microphone are used to recognize the user's emotions, and the emotion engine sends this information to the server. The server adjusts the suggestions based on the emotion information, suggesting additional special offer products if the user is happy, and suggesting products that will calm the user if the user is angry.

[0366] Examples of prompt statements Recommend new products based on the user's purchase and browsing history. Recognize the user's emotions and adjust the suggestions accordingly. For example, if the user is happy, add special offer products, if the user is angry, suggest products that will calm them down.

[0367] In this way, it becomes possible to make effective suggestions that take the user's emotions into account, and a highly convenient system that utilizes smartphones can be realized.

[0368] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0369] Step 1:

[0370] The server creates a list of companies in Japan. As input, it obtains attribute information such as the company's industry, size, and region from the database, and generates a company list based on this information. As output, it obtains a company list.

[0371] Step 2:

[0372] The server lists companies with the same attributes as good customers. The attribute information of good customers and the company list are used as input. Data processing involves filtering and listing companies that match the attributes of good customers. The list of companies with attributes is obtained as output.

[0373] Step 3:

[0374] The server uses the AI ​​model to compare the customer with good customers and simulate what proposals would improve the customer's performance. The input is the trading history and market trend data of good customers. As a data calculation, the AI ​​model analyzes this data and predicts the optimal proposal content. The proposal content is obtained as the output.

[0375] Step 4:

[0376] The server uses an emotion engine to recognize the user's emotions. As input, it uses facial expression images and voice data of the user sent from the smartphone. As data processing, the emotion engine analyzes these data and identifies the user's emotions. As output, emotion information is obtained.

[0377] Step 5:

[0378] The server adjusts the proposal content based on the emotion information. As input, it uses the proposal content obtained in step 3 and the emotion information obtained in step 4. As data calculation, it changes the proposal content according to the emotion information. For example, if the user is happy, it adds a special offer product, and if the user is angry, it suggests a product that calms the mood. As output, it obtains the adjusted proposal content.

[0379] Step 6:

[0380] The server generates a proposal policy and a proposal document and sends it to the smartphone. The adjusted proposal content is used as input. As data processing, the proposal content is converted into a document format and a proposal document is generated. As output, the proposal document is obtained and sent to the smartphone.

[0381] Step 7:

[0382] The smartphone displays the proposal received from the server to the user. As an input, the smartphone uses the proposal sent from the server. As a specific operation, the smartphone displays the proposal on the screen so that the user can view it. As an output, the user can confirm the contents of the proposal.

[0383] Step 8:

[0384] The user uses a smartphone to provide feedback on the proposal contents. As an input, the user inputs feedback based on the contents of the proposal. As a specific operation, the user inputs feedback through the smartphone interface and transmits it to the server. As an output, feedback data is obtained.

[0385] Step 9:

[0386] The server receives feedback from the user and reflects it in the next proposal. As input, it uses the user's feedback data. As data calculation, it analyzes the feedback data and uses it as learning data for the AI ​​model. As output, it obtains improved proposal content.

[0387] Example 2

[0388] Next, a second embodiment of the second embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0389] In the conventional system, it was difficult to make effective proposals when applying success stories of good customers to potential new business partners. In addition, the content of the proposals was not optimized to take into account the user's feelings, so the acceptability and effectiveness of the proposals was limited. This led to the issue that the business performance of potential new business partners was not improved sufficiently and new business development was not achieved.

[0390] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0391] In this invention, the server includes a means for creating a list of companies in Japan, a means for listing companies with attributes similar to those of good customers and making recommendations using a generative AI model, a means for comparing with good customers and simulating what proposals would improve customer performance using a generative AI model, a means for the generative AI model to generate a proposal policy and a proposal document, and an emotion engine that recognizes the user's emotions and optimizes the proposal content based on the emotions. This makes it possible to effectively apply success stories of good customers to new business partner candidates and make optimal proposals according to the user's emotions.

[0392] A "domestic company list" is a compilation in list form of information on companies located in Japan.

[0393] A "good customer" refers to a customer company that has a good track record of transactions in the past and has stable business performance.

[0394] "Attribute companies" refers to a group of companies that share a particular industry, size, or other characteristic.

[0395] A "generative AI model" refers to an algorithm or program that uses artificial intelligence technology to analyze data and make optimal suggestions and simulations.

[0396] "Recommending" refers to presenting the best options or suggestions based on specific criteria.

[0397] "Simulation" refers to virtually recreating a real-world situation and predicting the outcome.

[0398] "Proposal policy" refers to the basic direction and strategy of the proposal content.

[0399] A "proposal" is a written summary of the proposal contents, which includes a specific action plan and its effects.

[0400] An "emotion engine" refers to technology or a program that analyzes a user's emotions and generates optimal suggestions based on those emotions.

[0401] The present invention is a system for making proposals to potential new business partners based on success stories of good customers, and optimizing the content of the proposals based on the user's emotions. A specific embodiment of this system will be described below.

[0402] Hardware and Software Used

[0403] Hardware: Servers, terminals

[0404] Software: Generative AI models, emotion engine, database management system (DBMS)

[0405] Data collection

[0406] The server uses a database management system (DBMS) to collect performance data and past proposal data of good customers. The terminal collects the user's emotion data through an emotion engine. The emotion engine analyzes the user's emotions from their facial expressions and voice.

[0407] Data analysis

[0408] The server uses the collected data to analyze what kind of proposals good customers received that improved their performance. This analysis is performed using a generative AI model. The generative AI model learns from past proposals and performance data, and simulates proposal content for potential new business partners.

[0409] Proposal generation

[0410] The server generates a proposal for potential new business partners based on the simulation results, which describes specific actions, their effects, and the services that will be supported.

[0411] Emotional Optimization

[0412] The emotion engine recognizes the user's emotions and optimizes the content of suggestions based on those emotions. For example, if the user is feeling happy, the emotion engine will make suggestions that will amplify that joy. Conversely, if the user is feeling dissatisfied or angry, the emotion engine will make suggestions that will alleviate that dissatisfaction.

[0413] Examples

[0414] Valued customers: Major companies in the IT industry

[0415] Potential new business partners: Small and medium-sized businesses in the IT industry

[0416] Proposal content: Based on past proposals received from valued customers, we simulate how to improve the performance of potential new business partners and document a specific action plan in the proposal.

[0417] Examples of prompt statements If your best customers are large companies in the IT industry, list small and medium-sized companies in the same industry as potential new business partners. Based on what proposals your best customers received in the past that improved their performance, use AI to simulate whether a similar proposal would lead to improved performance for potential new business partners, and generate a proposal based on the results. Also, recognize the user's emotions and optimize the content of the proposal based on those emotions.

[0418] This system can effectively apply the success stories of good customers to potential new business partners and make optimal proposals based on the user's emotions, thereby helping to improve the business performance of potential new business partners and develop new business.

[0419] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0420] Step 1:

[0421] Data collection

[0422] The server uses a database management system (DBMS) to collect performance data and past proposal data of good customers. Specifically, the server executes an SQL query to retrieve required data from the database. The input is identification information of good customers, and the output is performance data and past proposal data of good customers. The terminal collects user emotion data through an emotion engine. Specifically, the terminal uses a camera and microphone to capture the user's facial expressions and voice, and transmits them to the emotion engine. The input is the user's real-time facial expression and voice data, and the output is analyzed emotion data.

[0423] Step 2:

[0424] Data analysis

[0425] Based on the collected data, the server analyzes what kind of proposals good customers received that improved their performance. A generative AI model is used for this analysis. Specifically, the server inputs data into the generative AI model, which then simulates the proposal content. The input is the performance data and past proposal data of good customers, and the output is the optimal proposal content as a result of the simulation. The generative AI model uses a neural network to analyze the data and generate the optimal proposal content.

[0426] Step 3:

[0427] Proposal generation

[0428] The server generates proposals for potential new business partners based on the simulation results. Specifically, the server embeds data in a proposal template based on the simulation results obtained from the generative AI model. The input is the optimal proposal content as a result of the simulation, and the output is the generated proposal. The proposal is generated in PDF or Word format and sent to the terminal.

[0429] Step 4:

[0430] Emotional Optimization

[0431] The emotion engine recognizes the user's emotion and optimizes the suggestions based on the emotion. Specifically, the emotion engine analyzes the user's emotion data and determines the emotional state. The input is the user's emotion data and the output is the determined emotional state. The server adjusts the suggestions based on the emotional state obtained from the emotion engine. The input is the determined emotional state and the output is optimized suggestions.

[0432] In this way, the system can effectively apply success stories of good customers to potential new business partners and make optimal proposals based on the user's emotions.

[0433] (Application example 2)

[0434] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0435] Conventional corporate proposal systems can make proposals to potential new business partners based on data on good customers, but they have the problem of being unable to make optimal proposals that take customer emotions into account. In addition, there was a lack of means to analyze customer emotions in real time and optimize proposal content based on that, making it difficult to increase customer satisfaction. Furthermore, there was no established method for effectively using prompt sentences when generating proposals using a generative AI model.

[0436] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0437] In this invention, the server includes a means for creating a list of companies in Japan, a means for listing companies with attributes similar to those of good customers and making recommendations using AI, a means for comparing with good customers and simulating with AI what proposals would improve customer performance, a means for generating a proposal policy and a proposal using AI, a means for recognizing customer emotions and optimizing the proposal content based on the emotions, a means for analyzing customer emotions in real time using a smart device, a means for generating a proposal using a generative AI model, and a means for generating a proposal using a prompt sentence. This makes it possible to make optimal proposals in real time that take into account customer emotions, thereby increasing customer satisfaction.

[0438] The "Domestic Company List" is a list that compiles information on companies located in Japan.

[0439] A "good customer" is a customer who is particularly valuable to a company and who does business with the company on an ongoing basis.

[0440] "Attribute companies" are a group of companies that share certain characteristics or conditions.

[0441] "AI recommendation" means using artificial intelligence to recommend specific companies or products.

[0442] "Simulation" means to virtually reproduce a real-world situation and make predictions and analyses.

[0443] A "proposal policy" is the basic direction or strategy of a proposal or plan.

[0444] A "proposal" is a document summarizing the contents of a specific proposal.

[0445] "Recognizing customer emotions" means analyzing the customer's emotions from their facial expressions, tone of voice, etc.

[0446] "Optimizing the proposal" means adjusting the proposal to best suit specific conditions or circumstances.

[0447] A "smart device" is an electronic device with Internet connectivity and advanced computing capabilities.

[0448] "Analyzing in real time" means processing data instantly and obtaining results.

[0449] A "generative AI model" is a model that is trained using artificial intelligence to perform a specific task.

[0450] A "prompt" is an instruction given to a generative AI model to obtain a particular output.

[0451] A system for carrying out the present invention has the following configuration: The server includes means for creating a list of companies in Japan, means for listing companies with similar attributes to good customers and using AI to recommend them, means for comparing with good customers and using AI to simulate what proposals would improve customer performance, means for AI to generate proposal guidelines and proposals, means for recognizing customer emotions and optimizing proposal content based on those emotions, means for analyzing customer emotions in real time using a smart device, means for generating proposals using a generative AI model, and means for generating proposals using prompt sentences.

[0452] Program processing explanation

[0453] The server first creates a list of companies in Japan. It then lists companies with similar attributes to good customers and uses artificial intelligence (AI) to recommend these companies. It compares the data with good customers and uses the AI ​​to simulate what proposals would improve the performance of potential new business partners. Based on the results of this simulation, the AI ​​generates a proposed policy and proposal document.

[0454] In addition, the server analyzes customer emotions in real time using smart devices (e.g. smart glasses). The smart device's camera and microphone are used to capture the customer's facial expressions and tone of voice. This data is analyzed using an emotion engine such as Microsoft Azure Cognitive Services. Based on the customer's emotions obtained as a result of the analysis, the content of the proposal is optimized.

[0455] When generating a proposal using a generative AI model (e.g., GPT-3 (registered trademark)), a prompt sentence is used. A prompt sentence is an instruction sentence input to a generative AI model to obtain a specific output. For example, the following prompt sentence is used.

[0456] Examples of prompt statements Customer Sentiments: Delight Customer Data: Data of loyal customers Proposal: Example

[0457] For example, when a customer is looking at a product through smart glasses in a brick-and-mortar store, a camera captures the customer's facial expression and recognizes "happiness" using the Azure Face API. The server uses GPT-3 to generate a proposal based on this emotion data and data on loyal customers. The generated proposal contains specific actions such as "If you purchase this product, you will receive an additional 10% off coupon."

[0458] In this way, it becomes possible to make optimal proposals in real time that take into account the customer's feelings, thereby increasing customer satisfaction.

[0459] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0460] Step 1:

[0461] The server creates a list of companies in Japan. As input, it obtains company information from a company database and processes it into a list format. As output, a list of companies in Japan is generated.

[0462] Step 2:

[0463] The server lists companies with similar attributes to good customers and uses AI to make recommendations. As input, it uses attribute data of good customers and a list of companies in Japan. The AI ​​analyzes this data and lists companies with matching attributes. As output, a list of recommended companies is generated.

[0464] Step 3:

[0465] The server compares the data with that of good customers and uses AI to simulate what proposals would improve the performance of potential new business partners. The performance data of good customers and the list of recommended companies are used as input. The AI ​​runs a simulation based on this data and generates optimal proposals. The simulation results are obtained as output.

[0466] Step 4:

[0467] The server uses the simulation results as input to generate a proposal policy and a proposal document using AI. The simulation results are used as input. Based on this, the AI ​​generates a specific proposal policy and proposal document. As output, a proposal policy and proposal document are generated.

[0468] Step 5:

[0469] The terminal (smart device) analyzes the customer's emotions in real time. As input, it uses facial and voice data of the customer acquired from the camera and microphone installed in the smart device. This data is analyzed by an emotion engine such as Microsoft Azure Cognitive Services. As output, it obtains the customer's emotion data.

[0470] Step 6:

[0471] The server optimizes the proposal content based on the customer's emotional data. As input, it uses the customer's emotional data, the proposal policy, and the proposal document. The AI ​​analyzes these data and adjusts the proposal content to the optimal content according to the emotion. As output, an optimized proposal document is generated.

[0472] Step 7:

[0473] The server uses the prompt to generate a proposal using a generative AI model (e.g. GPT-3). As input, it uses the prompt and the optimized proposal content. The generative AI model uses these data to generate the final proposal. As output, it obtains the completed proposal.

[0474] Examples of prompt statements Customer Sentiments: Delight Customer Data: Data of loyal customers Proposal:

[0475] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0476] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0477] Another example of generative AI is Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0478] In the above embodiment, an example was given in which the specific process was performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0479] [Second embodiment]

[0480] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0481] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0482] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0483] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0484] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0485] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0486] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0487] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0488] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0489] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0490] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0491] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0492] "Example 1"

[0493] One embodiment of the present invention is a system for developing new business partners using AI. This system creates a list of companies in Japan, and from that list, makes a list of companies that have similar attributes to good customers. The AI ​​performs analysis to make the list, taking into consideration attributes such as the company's industry, size, and region. Next, the AI ​​compares the company with good customers and simulates what proposals would improve the customer's performance. This simulation is performed based on past transaction history and market trends. Finally, the AI ​​generates a proposal plan and a proposal document based on the results. This proposal document includes the specific proposal content, its reasons, expected effects, etc.

[0494] "Example 2"

[0495] As a specific example, if a good client is a major company in the IT industry, small and medium-sized enterprises in the same industry will be listed as potential new business partners. Then, based on what proposals the good client received in the past that improved their performance, AI will simulate whether a similar proposal would lead to improved performance for the new business partner candidate. Based on the results, AI will generate a proposal for the new business partner candidate. This proposal will include specific actions that the new business partner candidate should take, their effects, and the services we provide to support those actions.

[0496] The process flow of each embodiment will be described below.

[0497] "Example 1"

[0498] Step 1: The AI ​​creates a list of companies in the country, including attributes such as the company's industry, size, and region.

[0499] Step 2: The AI ​​creates a list of companies that have similar attributes to good customers. This list is created by selecting companies that have similar attributes to good customers from the company list.

[0500] Step 3: The AI ​​compares the customer with a good customer and simulates what proposals would improve the customer's performance. This simulation is based on past transaction history, market trends, etc.

[0501] Step 4: The AI ​​generates a proposal based on the results of the simulation. This proposal includes the specific proposal content, its rationale, and the expected effects.

[0502] "Example 2"

[0503] Step 1: If the best customer is a large company in the IT industry, the AI ​​will list small and medium-sized companies in the same industry as potential new business partners.

[0504] Step 2: Based on what proposals good customers have received in the past that have improved their performance, the AI ​​simulates whether a similar proposal would lead to improved performance for a potential new business partner.

[0505] Step 3: Based on the results of the simulation, the AI ​​generates a proposal for the potential new business partner. This proposal describes the specific actions that the potential new business partner should take, their effects, and the services we provide to support those actions.

[0506] Example 1

[0507] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0508] In conventional systems for developing new business partners, creating company lists, listing companies with similar attributes to good customers, simulating proposal content, and generating proposal documents are often done manually, which can be problematic in terms of efficiency. In addition, the accuracy and effectiveness of the proposal content is uncertain, and it may not lead to an improvement in customer performance. This has created a demand for more efficient sales activities and more effective proposals.

[0509] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0510] In this invention, the server includes a means for creating a list of companies in Japan, a means for listing companies with similar attributes to good customers and using AI to recommend them, a means for comparing with good customers and using AI to simulate what proposals would improve customer performance, a means for AI to generate proposal guidelines and proposals based on the simulation results, and a means for generating proposals in natural language using a generative AI model. This makes it possible to efficiently develop new business partners and generate effective proposal content.

[0511] A "domestic company list" is a list that compiles information on companies located in Japan, including attributes such as the company's industry, size, and region.

[0512] A "good customer" is a customer with a good track record of transactions and excellent performance in the past, and is an important business partner for a company.

[0513] "Attributes" is information that indicates characteristics of a company, such as its industry, size, and region.

[0514] "AI recommendation" means using artificial intelligence to recommend the most suitable companies or proposals based on specific conditions.

[0515] "Simulation" is the process of predicting results under specific conditions based on past data and market trends.

[0516] The "proposal policy" indicates the basic direction and strategy of proposals to be made to customers.

[0517] A "proposal" is a document that describes the specific proposal to be made to a customer, its reasons, expected effects, etc.

[0518] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to generate sentences based on input prompts.

[0519] "Generating in natural language" means using artificial intelligence to create sentences in natural language that humans can understand.

[0520] This invention relates to a system for developing new business partners using AI. This system creates a list of companies in Japan, and from that list, lists companies that have similar attributes to good customers. It then simulates what proposals should be made to the listed companies to improve their customer performance, and generates proposals based on the results.

[0521] The server first retrieves company information from a domestic company database. This database contains attributes such as company industry, size, and region. The server uses SQL queries to extract the necessary data and create a company list. The server then uses an AI model to list companies that have similar attributes to good customers. Data analysis libraries such as scikit-learn and Pandas are used for this analysis. The server performs clustering based on company attributes such as industry, size, and region.

[0522] The server compares the listed companies with good customers and simulates what proposals would improve customer performance. This simulation is based on data such as past transaction history and market trends, and the AI ​​model makes predictions. Specifically, it performs regression analysis and clustering using past data.

[0523] Finally, the server generates a proposal policy and a proposal document based on the simulation results. The proposal document includes the specific proposal content, its rationale, expected effects, etc. Natural language processing (NLP) technology is used to generate the proposal document, utilizing a generative AI model.

[0524] A user instructs the system to create a list of new business partners, for example by inputting the following prompt into the generative AI model:

[0525] "Create a list of companies in your country that have similar attributes to your best customers. Then, run a simulation to see what proposals you could make to these companies to improve their performance, and generate proposals based on the results."

[0526] As a concrete example, a user instructs the system to "make a list of IT companies in Tokyo with more than 100 employees and make proposals for improving performance based on past transaction history." The server creates a list of companies based on the specified conditions and performs analysis and simulations using an AI model. Finally, a proposal is generated and provided to the user.

[0527] In this way, a system is realized in which the server, terminals, and users work together to efficiently develop new business partners.

[0528] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0529] Step 1: Create a list of companies

[0530] The server retrieves company information from a national company database. As input, a database containing company attributes such as industry, size, and region is used. The server uses SQL queries to extract the required data and create a company list. As output, a company list is generated.

[0531] Specific behavior:

[0532] The server executes a SQL query against the database:

[0533] sql SELECT FROM companies WHERE region = 'Japan';

[0534] This query retrieves company information for Japan.

[0535] Step 2: List companies with similar attributes to your best customers

[0536] The server uses an AI model to create a list of companies that have similar attributes to good customers. The list of companies and attribute information of good customers are used as input. The server performs clustering based on attributes such as the company's industry, size, and region. The list of companies is generated as output.

[0537] Specific behavior:

[0538] The server executes the following Python code to perform clustering.

[0539] python from sklearn.cluster import KMeans import pandas as pd Importing company data data = pd.read_csv('companies.csv') Running clustering kmeans = KMeans(n_clusters=5) clusters = kmeans.fit_predict(data[['industry', 'size', 'region']])

[0540] This code allows companies to be classified into clusters.

[0541] Step 3: Simulate the proposal

[0542] The server compares the listed companies with good customers and simulates what proposals would improve customer performance. As input, the server uses information on the listed companies, past transaction history, market trends, and other data. The server runs the simulation using regression analysis and predictive models. As output, it generates proposals.

[0543] Specific behavior:

[0544] The server runs the following Python code to perform the simulation:

[0545] python from sklearn.linear_model import LinearRegression Loading historical transaction data transaction_data = pd.read_csv('transactions.csv') Performing regression analysis model = LinearRegression() model.fit(transaction_data[['feature1', 'feature2']], transaction_data['performance']) Running a prediction predictions = model.predict(new_company_data[['feature1', 'feature2']])

[0546] This code predicts what proposals will be made to new business partners.

[0547] Step 4: Generate a proposal

[0548] The server generates a proposal policy and a proposal based on the simulation results. The simulation results are used as input. The server generates the proposal in natural language using a generative AI model. As output, a proposal is generated.

[0549] Specific behavior:

[0550] The server inputs the following prompt sentence into the generative AI model:

[0551] python prompt = """ Please prepare a proposal for a new business partner. Based on the information below, please include the specific proposal content, its justification, and the expected effects. Industry: IT Size: Medium Region: Tokyo Past transaction history: Yes Market trends: Growing """ response = gpt3.generate(prompt)

[0552] This code will generate a proposal.

[0553] Step 5: Submit your proposal

[0554] The user receives the generated proposal and makes a proposal to the new trading partner. As input, the generated proposal is used. As output, the proposal is provided to the new trading partner.

[0555] Specific behavior:

[0556] The user downloads the proposal generated from the system and submits it to the new business partner.

[0557] (Application example 1)

[0558] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0559] Conventional systems for developing new business partners have difficulty efficiently listing companies with similar attributes to good customers and making appropriate proposals. In addition, generating proposal content requires a lot of manual work, which is time-consuming and labor-intensive. Furthermore, the system is not user-friendly because it does not take into account use on mobile devices such as smartphones and tablets. To solve these problems, a more efficient and effective system for developing new business partners is needed.

[0560] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0561] In this invention, the server includes a means for creating a list of companies in Japan, a means for listing companies with attributes similar to those of good customers and making recommendations using AI, a means for comparing with good customers and simulating what proposals would improve customer performance, a means for generating a proposal policy and a proposal document using AI, a means for simulating proposal contents for new business partners, a means for automatically generating a proposal document using a generation AI model, and a means including an application to be installed on a smartphone or tablet. This makes it possible to efficiently and effectively develop new business partners and quickly generate proposal contents.

[0562] The "domestic company list" is a list that collects basic information about companies located in the country and stores it in a database.

[0563] A "good customer" is a customer who is deemed to be of particularly high transaction value based on past transaction history and business performance.

[0564] "Attribute companies" are companies that have specific attributes such as industry, size, or region.

[0565] "AI recommendation means" is a function that uses artificial intelligence to recommend companies based on specific conditions.

[0566] A "means of simulation" is a function that predicts future results based on past data and market trends.

[0567] The "proposal policy" indicates the basic direction and strategy of the proposal content.

[0568] A "proposal" is a document that describes the specific proposal content, its reasons, and the expected effects.

[0569] A "new business partner" is a new business partner with whom we have not had any transactions until now.

[0570] A "generative AI model" is a model that is trained using artificial intelligence to perform a specific task.

[0571] A "prompt sentence" is an instruction sentence input to a generative AI model.

[0572] An "application installed on a smartphone or tablet" is software that runs on a mobile device.

[0573] A system for implementing the present invention uses a server, a mobile device such as a smartphone or tablet, and a generative AI model. The specific configuration and operation of the system are described below.

[0574] System Configuration

[0575] 1. Server

[0576] The server creates a list of companies in Japan and stores it in a database. The server also runs an AI model to analyze the attributes of good customers and list companies with similar attributes. In addition, the server simulates proposals to new clients and automatically generates proposals using a generative AI model.

[0577] 2. Mobile Devices

[0578] An application that communicates with the server is installed on a mobile device such as a smartphone or tablet, and provides an interface for the user to view a list of potential business partners and to view proposals.

[0579] Data processing and calculation

[0580] 1. Creating a list of companies

[0581] The server collects information on companies in Japan and creates a database that includes attributes such as industry, size, and region. This data is managed using Pandas.

[0582] 2. Analysis of loyal customer attributes

[0583] The server analyzes the data of good customers using KMeans clustering and classifies them into specific clusters, which makes it possible to identify companies that have similar attributes to good customers.

[0584] 3. Listing new business partners

[0585] The server filters companies that have similar attributes to its best customers and creates a list of new business partners, which is then provided to the user through an application on their mobile device.

[0586] 4. Proposed Simulation

[0587] The server uses RandomForestRegressor to simulate proposals for new trading partners. This simulation is based on past trading history and market trends.

[0588] 5. Proposal Generation

[0589] The server uses the generative AI model to automatically generate a proposal. This proposal includes the specific proposal content, its rationale, and the expected effects. The generative AI model uses the OpenAI API.

[0590] Examples

[0591] For example, for manufacturing company A, we generate the following prompt:

[0592] Company name: Company A Industry: Manufacturing Scale: 100 Region: Tokyo Generate a proposal.

[0593] When this prompt sentence is input into the generative AI model, the AI ​​generates a specific proposal. For example, it may return a proposal such as, "The introduction of a new manufacturing line is expected to improve efficiency by 20%." In this way, users can make effective proposals to new business partners.

[0594] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0595] Step 1:

[0596] The server collects company information in the country and creates a database with attributes such as industry, size, region, etc. As input, it requires a data source of company information (e.g., a public company database) and as output, it obtains a list of companies in the form of a Pandas data frame. This data is used for subsequent analysis.

[0597] Step 2:

[0598] The server analyzes the data of good customers using KMeans clustering and classifies them into specific clusters. As input, it requires data of good customers (e.g. past transaction history, performance data), and as output, it obtains data of good customers with cluster labels. These cluster labels are used to identify the attributes of good customers.

[0599] Step 3:

[0600] The server filters companies with similar attributes to good customers and creates a list of new business partners. As input, it requires data of good customers with cluster labels and a list of companies in the country, and as output, it obtains a list of new business partners. This list is provided to the user through an application on the mobile device.

[0601] Step 4:

[0602] The server uses RandomForestRegressor to simulate proposals for new trading partners. As input, it requires a list of new trading partners and data on past trading history and market trends. As output, it obtains predictions of proposal contents. These predictions are used to generate proposal documents.

[0603] Step 5:

[0604] The server uses the generative AI model to automatically generate proposals. The inputs required are the predicted results of the proposal content and basic information about the new business partner (e.g. company name, industry, size, region), and the output is a proposal that includes the specific proposal content, its justification, and the expected effects. The generative AI model uses the OpenAI API.

[0605] Step 6:

[0606] A user views a list of new business partners and proposals through an application installed on a smartphone or tablet. As input, a list of new business partners and proposals provided by a server are required, and as output, they are displayed in a format that can be viewed by the user. This application provides an interface for the user to make effective proposals to new business partners.

[0607] Example 2

[0608] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0609] With the conventional system, it was difficult to make specific proposals to potential new business partners based on the success stories of good customers. In addition, it took a lot of time and effort to generate proposals, which made it difficult to conduct efficient sales activities.

[0610] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for creating a list of domestic companies, a means for listing companies with the same attributes as good customers and making recommendations using artificial intelligence, a means for comparing with good customers and simulating using artificial intelligence what proposals would improve customer performance, a means for generating a proposal based on the simulation results, and a means for providing the generated proposal to the user. This makes it possible to efficiently make specific proposals based on the success stories of good customers.

[0611] The "Domestic Company List" is a list that compiles information on companies located in Japan.

[0612] A "good customer" is a customer who has a good track record of transactions in the past and who can be expected to continue doing business with the company.

[0613] "Attribute companies" are companies that share a particular industry, size, or other common characteristics.

[0614] "Artificial intelligence" is a technology that enables computer systems to imitate human intelligence to learn and make inferences.

[0615] A "recommendation" is the suggestion of the best option based on specific criteria.

[0616] "Simulation" refers to the virtual reproduction of a real-world situation and predicting its outcomes.

[0617] A "proposal" is a document that documents a specific proposal and indicates specific actions to a business partner.

[0618] A "user" is someone who uses this system to create proposals and make them to business partners.

[0619] The present invention is a system for efficiently making specific proposals to potential new business partners based on success stories of good customers. A specific embodiment of this system will be described below.

[0620] The server first creates a list of companies in the country. To do this, a database management system (e.g., MySQL) is used to collect information on companies located in the country. Next, data on good customers is collected and past transaction records and performance data are analyzed. This analysis is performed using Python's Pandas library and NumPy library.

[0621] The server refers to an industry database to list companies with similar attributes to good customers. This allows small and medium-sized enterprises in the same industry to be extracted as potential new business partners. The extracted company list is recommended using artificial intelligence (e.g., generative AI model).

[0622] Next, the server simulates whether a proposal for a potential new business partner will lead to improved business performance based on the success stories of good customers. This simulation uses a generative AI model (e.g. GPT-4). Specific examples of prompt sentences include the following:

[0623] "Our good customer A has improved its performance in the past after receiving the following proposal. Please simulate what kind of effect you can expect if we make a similar proposal to a potential new business partner B."

[0624] Based on the simulation results, the server generates a proposal for the potential new business partner. This proposal describes the specific actions that the potential new business partner should take, their effects, and the services to support those actions. The generative AI model is used again to generate the proposal. Examples of specific prompt sentences include the following:

[0625] "Please prepare a proposal for potential new business partner B. In the proposal, please describe the specific actions that B should take, their effects, and the services we can provide to support those actions."

[0626] The generated proposal is provided to the user via the terminal. The user can make specific proposals to potential new business partners based on this proposal. This makes it possible to efficiently make specific proposals based on the success stories of good customers.

[0627] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0628] Step 1: Data collection

[0629] The server collects company information using a database management system (e.g., MySQL) to create a list of companies in Japan. As input, it obtains basic information about the companies (e.g., company name, location, industry, and size). As output, it generates a list of companies in Japan. Specifically, the server executes SQL queries to extract the required information from the database.

[0630] Step 2: Analyze your loyal customer data

[0631] The server collects and analyzes past transaction data and performance data of good customers. As input, it obtains transaction history and performance data of good customers. As output, it identifies successful proposals and factors that improved performance. Specifically, the server uses Python's Pandas library to analyze the data and extract success stories.

[0632] Step 3: List potential new business partners

[0633] The server refers to an industry database to list companies that have similar attributes as good customers. As input, it retrieves company information from the industry database. As output, it generates a list of potential new business partners. Specifically, the server executes an SQL query to extract companies that match the criteria.

[0634] Step 4: Simulation

[0635] The server simulates whether proposals for potential new business partners will lead to improved business performance, based on success stories of good customers. As input, it inputs the success stories of good customers and information on potential new business partners into the generative AI model. As output, it obtains the simulation results. In concrete terms, the server inputs the following prompt sentence into the generative AI model (e.g. GPT-4):

[0636] "Our good customer A has improved its performance in the past after receiving the following proposal. Please simulate what kind of effect you can expect if we make a similar proposal to a potential new business partner B."

[0637] Step 5: Generate a proposal

[0638] The server generates a proposal for a potential new business partner based on the simulation results. As input, it inputs the simulation results and information on the potential new business partner into the generative AI model. As output, a proposal is generated. Specifically, the server inputs the following prompt sentence into the generative AI model:

[0639] "Please prepare a proposal for potential new business partner B. In the proposal, please describe the specific actions that B should take, their effects, and the services we can provide to support those actions."

[0640] Step 6: Submit your proposal

[0641] The server sends the generated proposal to the terminal. As input, the server obtains the generated proposal. As output, the proposal is provided to the user. As a specific operation, the server sends the proposal to the terminal, and the terminal displays the proposal so that the user can confirm it. The user can make a specific proposal to a potential new business partner based on this proposal.

[0642] (Application example 2)

[0643] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server", and the smart glasses 214 will be referred to as a "terminal".

[0644] With conventional systems, it was difficult to make effective proposals to potential new business partners based on the success stories of good customers. In addition, there was a problem that efficient sales activities could not be carried out because it took a lot of time and effort to generate proposals. Furthermore, the content of the proposals sometimes lacked consistency, which could reduce the trust of potential new business partners. In order to solve these issues, there is a need for a system that can generate prompt sentences based on the success stories of good customers and automatically generate effective proposals using AI.

[0645] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0646] In this invention, the server includes a means for creating a list of companies in Japan, a means for listing companies with attributes similar to those of good customers and making recommendations using AI, a means for comparing with good customers and simulating what proposals would improve customer performance, a means for AI to generate a proposal policy and a proposal, a means for generating a prompt sentence based on success stories of good customers, a means for generating a proposal based on the generated prompt sentence, and a means for outputting a proposal for a new business partner candidate. This makes it possible to automatically generate effective proposals based on success stories of good customers quickly and consistently.

[0647] A "means for creating a domestic company list" is a method or device for collecting information on companies existing in the country and organizing it in list form.

[0648] "Means for compiling a list of companies with similar attributes to good customers and recommending them using AI" refers to a method or device for identifying companies that have similar characteristics to good customers and recommending these companies using artificial intelligence.

[0649] "A means of using AI to simulate what proposals will improve customer performance by comparing with good customers" refers to a method or device that compares data on good customers with data on potential new business partners and uses artificial intelligence to predict what kind of proposals will contribute to improving performance.

[0650] "Means for AI-generated proposal guidelines and written proposals" refers to methods or devices for automatically creating proposal guidelines and specific written proposals using artificial intelligence.

[0651] A "means for generating prompt sentences based on success stories of good customers" refers to a method or device for creating instruction sentences (prompt sentences) for artificial intelligence based on past success stories of good customers.

[0652] The "means for generating a proposal based on the generated prompt sentence" refers to a method or device for an artificial intelligence to automatically create a proposal using the generated prompt sentence as input.

[0653] The "means for outputting a proposal to a new supplier candidate" refers to a method or device for presenting the generated proposal to the new supplier candidate.

[0654] An embodiment of the present invention will now be described. First, the system uses the following hardware and software.

[0655] Hardware and Software Used

[0656] Hardware: Servers, smartphones

[0657] Software: Python, OpenAI API, Pandas

[0658] System Configuration

[0659] The server includes the following means:

[0660] 1. Means for creating a list of domestic companies: The server collects information on companies existing in the country and organizes it in the form of a list. This list includes basic information, business performance data, industry, etc. of the companies.

[0661] 2. Compiling a list of companies with similar attributes to those of best customers and using AI to recommend them: The server identifies companies with similar characteristics based on data on best customers and uses artificial intelligence to recommend these companies.

[0662] 3. A means of using AI to simulate what proposals would improve customer performance by comparing with best customers: The server compares data on best customers with data on potential new business partners, and uses artificial intelligence to predict what kind of proposals would contribute to improving performance.

[0663] 4. Means for AI to generate proposal guidelines and written proposals: The server uses artificial intelligence to automatically create proposal guidelines and specific written proposals.

[0664] 5. Means for generating prompt sentences based on success stories of good customers: The server creates instructions (prompt sentences) for the artificial intelligence based on past success stories of good customers.

[0665] 6. Means for generating a proposal based on the generated prompt sentence: The server uses the generated prompt sentence as input and the artificial intelligence automatically creates a proposal.

[0666] 7. Means for outputting a proposal to a potential new business partner: The server presents the generated proposal to the potential new business partner.

[0667] Data processing and calculation

[0668] The server collects data on good customers and potential new business partners, compares and analyzes this data, and uses Python and Pandas to read the data and OpenAI API to perform simulations and generate proposals using artificial intelligence.

[0669] Examples

[0670] For example, if a good customer is a "major IT company" that has been successful in the past when "SEO optimization and content marketing" was proposed to them, they can use that success story to make a similar proposal to a potential new business partner, a "small and medium-sized IT company."

[0671] Examples of prompt statements A valued client (a large IT company) saw an improvement in their business performance after receiving the following recommendations: SEO optimization and content marketing. Run a simulation to see if a similar recommendation would be effective for a potential new business partner (a small or medium-sized IT company).

[0672] In this way, the server can quickly and consistently automatically generate effective proposals based on best customer success stories.

[0673] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0674] Step 1:

[0675] The server creates a list of companies in Japan. Specifically, it collects basic information, performance data, industry, etc. of companies and organizes them in list form. As input, it uses company databases and publicly available company information, and as output, it generates an organized company list.

[0676] Step 2:

[0677] The server creates a list of companies with similar attributes to good customers and uses AI to make recommendations. Specifically, it identifies companies with similar characteristics based on the data of good customers and uses artificial intelligence to recommend these companies. It uses the data of good customers and the company list as input, and generates a list of recommended companies as output.

[0678] Step 3:

[0679] The server compares the data of good customers with those of potential new business partners and uses AI to simulate what proposals would improve the customer's performance. Specifically, it compares the data of good customers with that of potential new business partners and uses artificial intelligence to predict what proposals would contribute to improving performance. The server uses the data of good customers and the data of potential new business partners as input and generates the simulation results as output.

[0680] Step 4:

[0681] The server uses AI to generate the proposal policy and proposal document. Specifically, it uses artificial intelligence to automatically create the proposal policy and specific proposal document. It uses the simulation results as input and generates the proposal policy and proposal document as output.

[0682] Step 5:

[0683] The server generates a prompt sentence based on the success stories of good customers. Specifically, it creates an instruction sentence (prompt sentence) for the artificial intelligence based on the past success stories of good customers. The success story data of good customers is used as input, and the prompt sentence is generated as output.

[0684] Step 6:

[0685] The server generates a proposal based on the generated prompt. Specifically, the AI ​​automatically creates a proposal using the generated prompt as input. The server uses the prompt as input and generates a proposal as output.

[0686] Step 7:

[0687] The server outputs a proposal to the new supplier candidate. Specifically, the server presents the generated proposal to the new supplier candidate. The server uses the generated proposal as input, and generates a proposal to be presented to the new supplier candidate as output.

[0688] In addition, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0689] "Example 1"

[0690] In one embodiment of the present invention, the AI ​​includes an emotion engine that recognizes the user's emotions. The emotion engine reads emotions from the user's tone of voice, facial expressions, choice of words, etc. For example, if the user is happy or excited, the emotion engine conveys that information to the AI. The AI ​​adjusts the suggestions based on that information. Specifically, if the user is happy, the AI ​​makes suggestions to amplify that happiness. Also, if the user is frustrated or angry, the AI ​​makes suggestions to resolve that frustration.

[0691] "Example 2"

[0692] In another embodiment of the present invention, the emotion engine recognizes the user's emotion and optimizes the suggestions based on the emotion. Specifically, if the user feels happy, the AI ​​makes suggestions to amplify the joy. Also, if the user feels frustrated or angry, the AI ​​makes suggestions to resolve the frustration. This optimization is achieved by learning the correlation between the user's emotion and the suggestions. For example, the AI ​​analyzes past suggestions and the user's response to learn what suggestions will amplify the user's joy and what suggestions will resolve the user's frustration.

[0693] The process flow of each embodiment will be described below.

[0694] "Example 1"

[0695] Step 1: User interaction begins, either by the user asking the system a question or by the system providing information to the user.

[0696] Step 2: The emotion engine reads the user's emotions from their tone of voice, facial expressions, choice of words, etc.

[0697] Step 3: The emotion engine communicates the emotional information it has read to the AI.

[0698] Step 4: The AI ​​adjusts the suggestions based on the emotion information. Specifically, if the user is feeling happy, the AI ​​will make suggestions to amplify that happiness. Also, if the user is feeling dissatisfied or angry, the AI ​​will make suggestions to alleviate that dissatisfaction.

[0699] "Example 2"

[0700] Step 1: User interaction begins, either by the user asking the system a question or by the system providing information to the user.

[0701] Step 2: The emotion engine reads the user's emotions from their tone of voice, facial expressions, choice of words, etc.

[0702] Step 3: The emotion engine communicates the emotional information it has read to the AI.

[0703] Step 4: The AI ​​optimizes the content of the suggestions based on the emotion information. Specifically, if the user is feeling happy, the AI ​​will make suggestions to amplify that happiness. Also, if the user is feeling dissatisfied or angry, the AI ​​will make suggestions to alleviate that dissatisfaction.

[0704] Step 5: The AI ​​analyzes past suggestions and user responses to learn which suggestions will increase user delight and which suggestions will eliminate user dissatisfaction.

[0705] Example 1

[0706] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0707] In conventional new business partner development systems, the creation of company lists, attribute analysis of good customers, and generation of proposal content are often done manually, which is inefficient. In addition, the proposal content cannot be adjusted to take the user's feelings into account, which limits the effectiveness of the proposal. This creates the problem that companies are unable to fully improve their performance or develop new business partners.

[0708] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0709] In this invention, the server includes a means for creating a list of companies in Japan, a means for listing companies with attributes similar to those of good customers and making recommendations using artificial intelligence, a means for comparing with good customers and simulating using artificial intelligence what proposals would improve customer performance, a means for generating a proposal policy and a proposal document using artificial intelligence, and a means for adjusting the proposal contents using an emotion engine that recognizes the user's emotions. This makes it possible to efficiently create a list of companies, analyze the attributes of good customers, automatically generate proposal contents, and adjust the proposal contents according to the user's emotions.

[0710] A "domestic company list" is a list that collects information on companies that exist in Japan.

[0711] A "good customer" is a customer who has a good track record of transactions and business performance in the past.

[0712] "Attribute companies" refer to companies that are classified based on specific conditions (industry, size, region, etc.).

[0713] "Artificial intelligence" is a technology that uses machine learning and data analysis to mimic human intelligence.

[0714] A "recommendation" is the suggestion of the best option based on specific criteria.

[0715] "Simulation" refers to modeling real-world situations and conducting virtual experiments and predictions.

[0716] A "proposal" is a document that describes a specific proposal, its rationale, and the expected results.

[0717] The "emotion engine" is a technology that reads emotions from a user's tone of voice, facial expressions, choice of words, etc.

[0718] "Recommendations" refers to recommended actions or strategies for achieving a particular objective.

[0719] This invention is a system for developing new business partners using AI, which creates a list of companies in Japan and then selects from that list those with similar attributes to good customers. The system uses AI to perform analysis, taking into account attributes such as the company's industry, size, and region. Next, the AI ​​compares the company with good customers and simulates what proposals would improve the customer's performance. This simulation is performed based on past transaction history and market trends. Finally, the AI ​​generates a proposal policy and document based on the results. This proposal document includes the specific proposal content, its reasons, and expected effects.

[0720] Hardware and Software Used

[0721] Hardware: Servers, terminals

[0722] Software: AI models (e.g. TensorFlow, PyTorch), emotion engines (e.g. Affectiva, Microsoft Azure Emotion API)

[0723] Specific operation of the system

[0724] 1. Creating a list of companies:

[0725] The server extracts company information from a national company database.

[0726] The terminal provides an interface for inputting user-specified conditions (industry type, size, region, etc.).

[0727] The user inputs the conditions through a terminal.

[0728] The server uses an AI model to filter the list of companies based on the specified criteria.

[0729] The server transmits the filtering result to the terminal.

[0730] The terminal displays the filtering results to the user.

[0731] 2. Attribute analysis of loyal customers:

[0732] The server collects data on loyal customers.

[0733] The terminal provides an interface for inputting information on preferred customers provided by the user.

[0734] The user inputs information about good customers through the terminal.

[0735] The server uses an AI model to analyze attributes of good customers, such as industry, size, and region.

[0736] Based on the analysis results, the server compiles a list of similar companies.

[0737] The server transmits the list result to the terminal.

[0738] The terminal displays the listing results to the user.

[0739] 3. Proposed simulation:

[0740] The server collects past trading history and market trend data.

[0741] The server uses an AI model to simulate what proposals would improve customer performance.

[0742] The server transmits the simulation results to the terminal.

[0743] The terminal displays the simulation results to the user.

[0744] 4. Proposal Generation:

[0745] The server decides on a proposal policy based on the simulation results.

[0746] The server uses the AI ​​model to generate a proposal that includes specific proposal details, their rationale, and expected benefits.

[0747] The server transmits the generated proposal to the terminal.

[0748] The terminal displays the proposal to the user.

[0749] 5. Using the Emotion Engine:

[0750] The device uses an emotion engine to analyze the user's tone of voice, facial expressions, choice of words, etc.

[0751] The emotion engine sends the analysis results to the server.

[0752] The server uses an AI model to tailor its suggestions based on the user's emotions.

[0753] The server sends the adjusted proposal to the terminal.

[0754] The device displays the proposed adjustments to the user.

[0755] Examples and prompts

[0756] Examples:

[0757] If a user is looking to develop new business partners, the system will list companies from a list of domestic companies based on the following criteria: industry (manufacturing), size (small and medium-sized enterprises), and region (Kanto region).

[0758] Designate "A Co., Ltd." as a valued customer and list similar companies based on its attributes.

[0759] Based on past transaction history and market trends, the system suggests "introducing product B," citing as its justification that "sales increased by 20% in past implementation cases."

[0760] When the user is reviewing the proposal, the emotion engine reads the "excitement" from the user's facial expression and further emphasizes the proposal.

[0761] Example prompt: In order to develop new business partners, please make a list of companies from a list of domestic companies with the following criteria: industry (manufacturing), size (small and medium-sized enterprises), and region (Kanto region). Specify "Corporation A" as a good customer, and make a list of similar companies based on that attribute. Based on past transaction history and market trends, simulate what proposals would improve the customer's performance, and generate a proposal that includes specific proposal content, its reasons, and the expected effects.

[0762] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0763] Step 1:

[0764] Creating a company list

[0765] Input: The user enters conditions such as industry, size, and region into the terminal.

[0766] Specific operation: The terminal receives the conditions specified by the user and sends them to the server.

[0767] Data processing: The server extracts company information that matches the specified conditions from the company database.

[0768] Output: The server generates the filtered list of companies and sends it to the terminal.

[0769] Specific operation: The terminal displays the filtering results to the user in list form.

[0770] Step 2:

[0771] Attribute analysis of loyal customers

[0772] Input: The user enters preferred customer information into the terminal.

[0773] Specific operation: The terminal receives the information on good customers provided by the user and transmits it to the server.

[0774] Data processing: The server collects data on good customers and uses an AI model to analyze attributes such as industry, size, and region.

[0775] Output: Based on the analysis results, the server creates a list of similar companies and sends it to the terminal.

[0776] Specific behavior: The terminal displays the listing results to the user.

[0777] Step 3:

[0778] Proposal Simulation

[0779] Input: The server collects historical trading and market trend data.

[0780] What happens: The server inputs this data into the AI ​​model.

[0781] Data calculation: The AI ​​model simulates what recommendations would improve customer performance.

[0782] Output: The server generates the simulation results and sends them to the terminal.

[0783] Specific operation: The terminal displays the simulation results to the user.

[0784] Step 4:

[0785] Proposal Generation

[0786] Input: The server receives the simulation results.

[0787] Specific operation: The server uses the AI ​​model to generate a proposal that includes specific proposal content, its rationale, and the expected effects.

[0788] Data processing: Format the proposal content and put it into document format.

[0789] Output: The server sends the generated proposal to the terminal.

[0790] Specific behavior: The device displays the proposal to the user.

[0791] Step 5:

[0792] Using the Emotion Engine

[0793] Input: The device collects the user's tone of voice, facial expressions, word choice, etc.

[0794] Specific operation: The device inputs the collected data into the emotion engine.

[0795] Data calculation: The emotion engine analyzes the user's emotion and sends the result to the server.

[0796] Output: The server receives the sentiment analysis results and uses the AI ​​model to refine the suggestions.

[0797] Specific operation: The server sends the adjusted proposal to the device, which then displays it to the user.

[0798] (Application example 1)

[0799] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0800] Conventional systems for developing new business partners can create company lists and generate proposals, but they do not adjust the content of the proposals to take into account the user's feelings, which means that the effectiveness of the proposals is limited. In addition, there is a lack of systems that utilize mobile devices such as smartphones, which also creates a problem of low user convenience.

[0801] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0802] In this invention, the server includes a means for creating a list of companies in Japan, a means for listing companies with attributes similar to those of good customers and making recommendations using AI, a means for comparing with good customers and simulating with AI what proposals would improve customer performance, a means for AI to generate a proposal policy and proposal, a means for adjusting the proposal content using an emotion engine that recognizes the user's emotions, and a means including an application to be installed on a smartphone. This enables effective proposals that take the user's emotions into consideration, and realizes a highly convenient system that utilizes smartphones.

[0803] The "company list" is a database that compiles domestic companies in a list format, and includes attribute information such as the company's industry, size, and region.

[0804] A "good customer" is one who is particularly valuable based on past transaction history and business performance.

[0805] "Attribute companies" refer to companies that have similar attributes, such as industry, size, and region, as good customers.

[0806] "Recommendation" means that AI performs analysis and suggests the best options based on certain conditions.

[0807] "Simulation" means that AI predicts what results a particular proposal will bring, based on past data and market trends.

[0808] A "proposal" is a document generated by AI that includes the specific proposal content, its rationale, expected effects, etc.

[0809] The "emotion engine" is a system that reads emotions from the user's tone of voice, facial expressions, choice of words, etc., and conveys that information to the AI.

[0810] A "smartphone" is a type of mobile phone, a multi-function device that can connect to the Internet and install applications.

[0811] An "application" is software installed on a smartphone that provides specific functions or services.

[0812] The following system configuration will be described as an embodiment of the present invention.

[0813] System Configuration

[0814] Hardware

[0815] Server: Manages the database, runs the AI ​​models, and processes the emotion engine.

[0816] Smartphone: Functions as a user interface and recognizes the user's emotions using a camera and microphone.

[0817] software

[0818] Database: Stores a list of companies within the country and manages data to create a list of companies with similar attributes to good customers.

[0819] AI model: A generative AI model that suggests products based on a user's purchasing history and browsing history.

[0820] Emotion engine: Software that detects emotions from a user's tone of voice, facial expressions, choice of words, etc.

[0821] Application: An application that is installed on a smartphone and allows the user to interact with it.

[0822] Data processing and calculation

[0823] server

[0824] The server first creates a list of companies in Japan, listing companies with attributes similar to those of good customers. It then uses an AI model to compare these companies with good customers and simulate what proposals would improve their performance. It also uses an emotion engine to recognize the user's emotions and adjusts the content of the proposals based on that information. Finally, it generates a proposed policy and proposal document and sends them to the smartphone.

[0825] Smartphone

[0826] The smartphone collects the user's purchase history and browsing history and sends them to the server. It also uses a camera and microphone to analyze the user's facial expressions and tone of voice and sends them to the emotion engine. The proposals received from the server are displayed to the user and an interaction takes place.

[0827] Examples

[0828] For example, when a user uses a smartphone to access an online shopping site, their purchase history and browsing history are sent to the server. Based on this data, the server uses an AI model to suggest new products. In addition, the smartphone's camera and microphone are used to recognize the user's emotions, and the emotion engine sends this information to the server. The server adjusts the suggestions based on the emotion information, suggesting additional special offer products if the user is happy, and suggesting products that will calm the user if the user is angry.

[0829] Examples of prompt statements Recommend new products based on the user's purchase and browsing history. Recognize the user's emotions and adjust the suggestions accordingly. For example, if the user is happy, add special offer products, if the user is angry, suggest products that will calm them down.

[0830] In this way, it becomes possible to make effective suggestions that take the user's emotions into account, and a highly convenient system that utilizes smartphones can be realized.

[0831] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0832] Step 1:

[0833] The server creates a list of companies in Japan. As input, it obtains attribute information such as the company's industry, size, and region from the database, and generates a company list based on this information. As output, it obtains a company list.

[0834] Step 2:

[0835] The server lists companies with the same attributes as good customers. The attribute information of good customers and the company list are used as input. Data processing involves filtering and listing companies that match the attributes of good customers. The list of companies with attributes is obtained as output.

[0836] Step 3:

[0837] The server uses the AI ​​model to compare the customer with good customers and simulate what proposals would improve the customer's performance. The input is the trading history and market trend data of good customers. As a data calculation, the AI ​​model analyzes this data and predicts the optimal proposal content. The proposal content is obtained as the output.

[0838] Step 4:

[0839] The server uses an emotion engine to recognize the user's emotions. As input, it uses facial expression images and voice data of the user sent from the smartphone. As data processing, the emotion engine analyzes these data and identifies the user's emotions. As output, emotion information is obtained.

[0840] Step 5:

[0841] The server adjusts the proposal content based on the emotion information. As input, it uses the proposal content obtained in step 3 and the emotion information obtained in step 4. As data calculation, it changes the proposal content according to the emotion information. For example, if the user is happy, it adds a special offer product, and if the user is angry, it suggests a product that calms the mood. As output, it obtains the adjusted proposal content.

[0842] Step 6:

[0843] The server generates a proposal policy and a proposal document and sends it to the smartphone. The adjusted proposal content is used as input. As data processing, the proposal content is converted into a document format and a proposal document is generated. As output, the proposal document is obtained and sent to the smartphone.

[0844] Step 7:

[0845] The smartphone displays the proposal received from the server to the user. As an input, the smartphone uses the proposal sent from the server. As a specific operation, the smartphone displays the proposal on the screen so that the user can view it. As an output, the user can confirm the contents of the proposal.

[0846] Step 8:

[0847] The user uses a smartphone to provide feedback on the proposal contents. As an input, the user inputs feedback based on the contents of the proposal. As a specific operation, the user inputs feedback through the smartphone interface and transmits it to the server. As an output, feedback data is obtained.

[0848] Step 9:

[0849] The server receives feedback from the user and reflects it in the next proposal. As input, it uses the user's feedback data. As data calculation, it analyzes the feedback data and uses it as learning data for the AI ​​model. As output, it obtains improved proposal content.

[0850] Example 2

[0851] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0852] In the conventional system, it was difficult to make effective proposals when applying success stories of good customers to potential new business partners. In addition, the content of the proposals was not optimized to take into account the user's feelings, so the acceptability and effectiveness of the proposals was limited. This led to the issue that the business performance of potential new business partners was not improved sufficiently and new business development was not achieved.

[0853] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0854] In this invention, the server includes a means for creating a list of companies in Japan, a means for listing companies with attributes similar to those of good customers and making recommendations using a generative AI model, a means for comparing with good customers and simulating what proposals would improve customer performance using a generative AI model, a means for the generative AI model to generate a proposal policy and a proposal document, and an emotion engine that recognizes the user's emotions and optimizes the proposal content based on the emotions. This makes it possible to effectively apply success stories of good customers to new business partner candidates and make optimal proposals according to the user's emotions.

[0855] A "domestic company list" is a compilation in list form of information on companies located in Japan.

[0856] A "good customer" refers to a customer company that has a good track record of transactions in the past and has stable business performance.

[0857] "Attribute companies" refers to a group of companies that share a particular industry, size, or other characteristic.

[0858] A "generative AI model" refers to an algorithm or program that uses artificial intelligence technology to analyze data and make optimal suggestions and simulations.

[0859] "Recommending" refers to presenting the best options or suggestions based on specific criteria.

[0860] "Simulation" refers to virtually recreating a real-world situation and predicting the outcome.

[0861] "Proposal policy" refers to the basic direction and strategy of the proposal content.

[0862] A "proposal" is a written summary of the proposal contents, which includes a specific action plan and its effects.

[0863] An "emotion engine" refers to technology or a program that analyzes a user's emotions and generates optimal suggestions based on those emotions.

[0864] The present invention is a system for making proposals to potential new business partners based on success stories of good customers, and optimizing the content of the proposals based on the user's emotions. A specific embodiment of this system will be described below.

[0865] Hardware and Software Used

[0866] Hardware: Servers, terminals

[0867] Software: Generative AI models, emotion engine, database management system (DBMS)

[0868] Data collection

[0869] The server uses a database management system (DBMS) to collect performance data and past proposal data of good customers. The terminal collects the user's emotion data through an emotion engine. The emotion engine analyzes the user's emotions from their facial expressions and voice.

[0870] Data analysis

[0871] The server uses the collected data to analyze what kind of proposals good customers received that improved their performance. This analysis is performed using a generative AI model. The generative AI model learns from past proposals and performance data, and simulates proposal content for potential new business partners.

[0872] Proposal generation

[0873] The server generates a proposal for potential new business partners based on the simulation results, which describes specific actions, their effects, and the services that will be supported.

[0874] Emotional Optimization

[0875] The emotion engine recognizes the user's emotions and optimizes the content of suggestions based on those emotions. For example, if the user is feeling happy, the emotion engine will make suggestions that will amplify that happiness. Conversely, if the user is feeling dissatisfied or angry, the emotion engine will make suggestions that will alleviate that dissatisfaction.

[0876] Examples

[0877] Valued customers: Major companies in the IT industry

[0878] Potential new business partners: Small and medium-sized businesses in the IT industry

[0879] Proposal content: Based on past proposals received from valued customers, we simulate how to improve the performance of potential new business partners and document a specific action plan in the proposal.

[0880] Examples of prompt statements If your best customers are large companies in the IT industry, list small and medium-sized companies in the same industry as potential new business partners. Based on what proposals your best customers received in the past that improved their performance, use AI to simulate whether a similar proposal would lead to improved performance for potential new business partners, and generate a proposal based on the results. Also, recognize the user's emotions and optimize the content of the proposal based on those emotions.

[0881] This system can effectively apply the success stories of good customers to potential new business partners and make optimal proposals based on the user's emotions, thereby helping to improve the business performance of potential new business partners and develop new business.

[0882] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0883] Step 1:

[0884] Data collection

[0885] The server uses a database management system (DBMS) to collect performance data and past proposal data of good customers. Specifically, the server executes an SQL query to retrieve required data from the database. The input is identification information of good customers, and the output is performance data and past proposal data of good customers. The terminal collects user emotion data through an emotion engine. Specifically, the terminal uses a camera and microphone to capture the user's facial expressions and voice, and transmits them to the emotion engine. The input is the user's real-time facial expression and voice data, and the output is analyzed emotion data.

[0886] Step 2:

[0887] Data analysis

[0888] Based on the collected data, the server analyzes what kind of proposals good customers received that improved their performance. A generative AI model is used for this analysis. Specifically, the server inputs data into the generative AI model, which then simulates the proposal content. The input is the performance data and past proposal data of good customers, and the output is the optimal proposal content as a result of the simulation. The generative AI model uses a neural network to analyze the data and generate the optimal proposal content.

[0889] Step 3:

[0890] Proposal generation

[0891] The server generates proposals for potential new business partners based on the simulation results. Specifically, the server embeds data in a proposal template based on the simulation results obtained from the generative AI model. The input is the optimal proposal content as a result of the simulation, and the output is the generated proposal. The proposal is generated in PDF or Word format and sent to the terminal.

[0892] Step 4:

[0893] Emotional Optimization

[0894] The emotion engine recognizes the user's emotion and optimizes the suggestions based on the emotion. Specifically, the emotion engine analyzes the user's emotion data and determines the emotional state. The input is the user's emotion data and the output is the determined emotional state. The server adjusts the suggestions based on the emotional state obtained from the emotion engine. The input is the determined emotional state and the output is optimized suggestions.

[0895] In this way, the system can effectively apply success stories of good customers to potential new business partners and make optimal proposals based on the user's emotions.

[0896] (Application example 2)

[0897] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server", and the smart glasses 214 will be referred to as a "terminal".

[0898] Conventional corporate proposal systems can make proposals to potential new business partners based on data on good customers, but they have the problem of being unable to make optimal proposals that take customer emotions into account. In addition, there was a lack of means to analyze customer emotions in real time and optimize proposal content based on that, making it difficult to increase customer satisfaction. Furthermore, there was no established method for effectively using prompt sentences when generating proposals using a generative AI model.

[0899] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0900] In this invention, the server includes a means for creating a list of companies in Japan, a means for listing companies with attributes similar to those of good customers and making recommendations using AI, a means for comparing with good customers and simulating with AI what proposals would improve customer performance, a means for generating a proposal policy and a proposal using AI, a means for recognizing customer emotions and optimizing the proposal content based on the emotions, a means for analyzing customer emotions in real time using a smart device, a means for generating a proposal using a generative AI model, and a means for generating a proposal using a prompt sentence. This makes it possible to make optimal proposals in real time that take into account customer emotions, thereby increasing customer satisfaction.

[0901] The "Domestic Company List" is a list that compiles information on companies located in Japan.

[0902] A "good customer" is a customer who is particularly valuable to a company and who does business with the company on an ongoing basis.

[0903] "Attribute companies" are a group of companies that share certain characteristics or conditions.

[0904] "AI recommendation" means using artificial intelligence to recommend specific companies or products.

[0905] "Simulation" means to virtually reproduce a real-world situation and make predictions and analyses.

[0906] A "proposal policy" is the basic direction or strategy of a proposal or plan.

[0907] A "proposal" is a document summarizing the contents of a specific proposal.

[0908] "Recognizing customer emotions" means analyzing the customer's emotions from their facial expressions, tone of voice, etc.

[0909] "Optimizing the proposal" means adjusting the proposal to best suit specific conditions or circumstances.

[0910] A "smart device" is an electronic device with Internet connectivity and advanced computing capabilities.

[0911] "Analyzing in real time" means processing data instantly and obtaining results.

[0912] A "generative AI model" is a model that is trained using artificial intelligence to perform a specific task.

[0913] A "prompt" is an instruction given to a generative AI model to obtain a particular output.

[0914] A system for carrying out the present invention has the following configuration: The server includes means for creating a list of companies in Japan, means for listing companies with similar attributes to good customers and using AI to recommend them, means for comparing with good customers and using AI to simulate what proposals would improve customer performance, means for AI to generate proposal guidelines and proposals, means for recognizing customer emotions and optimizing proposal content based on those emotions, means for analyzing customer emotions in real time using a smart device, means for generating proposals using a generative AI model, and means for generating proposals using prompt sentences.

[0915] Program processing explanation

[0916] The server first creates a list of companies in Japan. It then lists companies with similar attributes to good customers and uses artificial intelligence (AI) to recommend these companies. It compares the data with good customers and uses the AI ​​to simulate what proposals would improve the performance of potential new business partners. Based on the results of this simulation, the AI ​​generates a proposed policy and proposal document.

[0917] In addition, the server analyzes customer emotions in real time using smart devices (e.g. smart glasses). The smart device's camera and microphone are used to capture the customer's facial expressions and tone of voice. This data is analyzed using an emotion engine such as Microsoft Azure Cognitive Services. Based on the customer's emotions obtained as a result of the analysis, the content of the proposal is optimized.

[0918] When generating a proposal using a generative AI model (e.g. GPT-3), a prompt sentence is used. A prompt sentence is an instruction sentence input to the generative AI model to obtain a specific output. For example, the following prompt sentence is used.

[0919] Examples of prompt statements Customer Sentiments: Delight Customer Data: Data of loyal customers

[0920] For example, when a customer is looking at a product through smart glasses in a brick-and-mortar store, a camera captures the customer's facial expression and recognizes "happiness" using the Azure Face API. The server uses GPT-3 to generate a proposal based on this emotion data and data on loyal customers. The generated proposal contains specific actions such as "If you purchase this product, you will receive an additional 10% off coupon."

[0921] In this way, it becomes possible to make optimal proposals in real time that take into account the customer's feelings, thereby increasing customer satisfaction.

[0922] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0923] Step 1:

[0924] The server creates a list of companies in Japan. As input, it obtains company information from a company database and processes it into a list format. As output, a list of companies in Japan is generated.

[0925] Step 2:

[0926] The server lists companies with similar attributes to good customers and uses AI to make recommendations. As input, it uses attribute data of good customers and a list of companies in Japan. The AI ​​analyzes this data and lists companies with matching attributes. As output, a list of recommended companies is generated.

[0927] Step 3:

[0928] The server compares the data with that of good customers and uses AI to simulate what proposals would improve the performance of potential new business partners. The performance data of good customers and the list of recommended companies are used as input. The AI ​​runs a simulation based on this data and generates optimal proposals. The simulation results are obtained as output.

[0929] Step 4:

[0930] The server uses the simulation results as input to generate a proposal policy and a proposal document using AI. The simulation results are used as input. Based on this, the AI ​​generates a specific proposal policy and proposal document. As output, a proposal policy and proposal document are generated.

[0931] Step 5:

[0932] The terminal (smart device) analyzes the customer's emotions in real time. As input, it uses facial and voice data of the customer acquired from the camera and microphone installed in the smart device. This data is analyzed by an emotion engine such as Microsoft Azure Cognitive Services. As output, it obtains the customer's emotion data.

[0933] Step 6:

[0934] The server optimizes the proposal content based on the customer's emotional data. As input, it uses the customer's emotional data, the proposal policy, and the proposal document. The AI ​​analyzes these data and adjusts the proposal content to the optimal content according to the emotion. As output, an optimized proposal document is generated.

[0935] Step 7:

[0936] The server uses the prompt to generate a proposal using a generative AI model (e.g. GPT-3). As input, it uses the prompt and the optimized proposal content. The generative AI model uses these data to generate the final proposal. As output, it obtains the completed proposal.

[0937] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0938] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. A data generation model 58 is obtained by performing deep learning on a neural network.

[0939] A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0940] Another example of generative AI is Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0941] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0942] [Third embodiment]

[0943] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0944] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0945] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0946] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0947] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0948] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0949] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0950] Fig. 6 shows an example of main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0951] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0952] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0953] In the headset type terminal 314, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0954] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0955] "Example 1"

[0956] One embodiment of the present invention is a system for developing new business partners using AI. This system creates a list of companies in Japan, and from that list, makes a list of companies that have similar attributes to good customers. The AI ​​performs analysis to make the list, taking into consideration attributes such as the company's industry, size, and region. Next, the AI ​​compares the company with good customers and simulates what proposals would improve the customer's performance. This simulation is performed based on past transaction history and market trends. Finally, the AI ​​generates a proposal plan and a proposal document based on the results. This proposal document includes the specific proposal content, its reasons, expected effects, etc.

[0957] "Example 2"

[0958] As a specific example, if a good client is a major company in the IT industry, small and medium-sized enterprises in the same industry will be listed as potential new business partners. Then, based on what proposals the good client received in the past that improved their performance, AI will simulate whether a similar proposal would lead to improved performance for the new business partner candidate. Based on the results, AI will generate a proposal for the new business partner candidate. This proposal will include specific actions that the new business partner candidate should take, their effects, and the services we provide to support those actions.

[0959] The process flow of each embodiment will be described below.

[0960] "Example 1"

[0961] Step 1: The AI ​​creates a list of companies in the country, including attributes such as the company's industry, size, and region.

[0962] Step 2: The AI ​​creates a list of companies that have similar attributes to good customers. This list is created by selecting companies that have similar attributes to good customers from the company list.

[0963] Step 3: The AI ​​compares the customer with a good customer and simulates what proposals would improve the customer's performance. This simulation is based on past transaction history, market trends, etc.

[0964] Step 4: The AI ​​generates a proposal based on the results of the simulation. This proposal includes the specific proposal content, its rationale, and the expected effects.

[0965] "Example 2"

[0966] Step 1: If the best customer is a large company in the IT industry, the AI ​​will list small and medium-sized companies in the same industry as potential new business partners.

[0967] Step 2: Based on what proposals good customers have received in the past that have improved their performance, the AI ​​simulates whether a similar proposal would lead to improved performance for a potential new business partner.

[0968] Step 3: Based on the results of the simulation, the AI ​​generates a proposal for the potential new business partner. This proposal describes the specific actions that the potential new business partner should take, their effects, and the services we provide to support those actions.

[0969] Example 1

[0970] Next, a description will be given of Example 1 of the embodiment 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal".

[0971] In conventional systems for developing new business partners, creating company lists, listing companies with similar attributes to good customers, simulating proposal content, and generating proposal documents are often done manually, which can be problematic in terms of efficiency. In addition, the accuracy and effectiveness of the proposal content is uncertain, and it may not lead to an improvement in customer performance. This has created a demand for more efficient sales activities and more effective proposals.

[0972] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0973] In this invention, the server includes a means for creating a list of companies in Japan, a means for listing companies with similar attributes to good customers and using AI to recommend them, a means for comparing with good customers and using AI to simulate what proposals would improve customer performance, a means for AI to generate proposal guidelines and proposals based on the simulation results, and a means for generating proposals in natural language using a generative AI model. This makes it possible to efficiently develop new business partners and generate effective proposal content.

[0974] A "domestic company list" is a list that compiles information on companies located in Japan, including attributes such as the company's industry, size, and region.

[0975] A "good customer" is a customer with a good track record of transactions and excellent performance in the past, and is an important business partner for a company.

[0976] "Attributes" is information that indicates characteristics of a company, such as its industry, size, and region.

[0977] "AI recommendation" means using artificial intelligence to recommend the most suitable companies or proposals based on specific conditions.

[0978] "Simulation" is the process of predicting results under specific conditions based on past data and market trends.

[0979] The "proposal policy" indicates the basic direction and strategy of proposals to be made to customers.

[0980] A "proposal" is a document that describes the specific proposal to be made to a customer, its reasons, expected effects, etc.

[0981] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to generate sentences based on input prompts.

[0982] "Generating in natural language" means using artificial intelligence to create sentences in natural language that humans can understand.

[0983] This invention relates to a system for developing new business partners using AI. This system creates a list of companies in Japan, and from that list, lists companies that have similar attributes to good customers. It then simulates what proposals should be made to the listed companies to improve their customer performance, and generates proposals based on the results.

[0984] The server first retrieves company information from a domestic company database. This database contains attributes such as company industry, size, and region. The server uses SQL queries to extract the necessary data and create a company list. The server then uses an AI model to list companies that have similar attributes to good customers. Data analysis libraries such as scikit-learn and Pandas are used for this analysis. The server performs clustering based on company attributes such as industry, size, and region.

[0985] The server compares the listed companies with good customers and simulates what proposals would improve customer performance. This simulation is based on data such as past transaction history and market trends, and the AI ​​model makes predictions. Specifically, it performs regression analysis and clustering using past data.

[0986] Finally, the server generates a proposal policy and a proposal document based on the simulation results. The proposal document includes the specific proposal content, its rationale, expected effects, etc. Natural language processing (NLP) technology is used to generate the proposal document, utilizing a generative AI model.

[0987] A user instructs the system to create a list of new business partners, for example by inputting the following prompt into the generative AI model:

[0988] "Create a list of companies in your country that have similar attributes to your best customers. Then, run a simulation to see what proposals you could make to these companies to improve their performance, and generate proposals based on the results."

[0989] As a concrete example, a user instructs the system to "make a list of IT companies in Tokyo with more than 100 employees and make proposals for improving performance based on past transaction history." The server creates a list of companies based on the specified conditions and performs analysis and simulations using an AI model. Finally, a proposal is generated and provided to the user.

[0990] In this way, a system is realized in which the server, terminals, and users work together to efficiently develop new business partners.

[0991] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0992] Step 1: Create a list of companies

[0993] The server retrieves company information from a national company database. As input, a database containing company attributes such as industry, size, and region is used. The server uses SQL queries to extract the required data and create a company list. As output, a company list is generated.

[0994] Specific behavior:

[0995] The server executes a SQL query against the database:

[0996] sql SELECT FROM companies WHERE region = 'Japan';

[0997] This query retrieves company information for Japan.

[0998] Step 2: List companies with similar attributes to your best customers

[0999] The server uses an AI model to create a list of companies that have similar attributes to good customers. The list of companies and attribute information of good customers are used as input. The server performs clustering based on attributes such as the company's industry, size, and region. The list of companies is generated as output.

[1000] Specific behavior:

[1001] The server executes the following Python code to perform clustering.

[1002] python from sklearn.cluster import KMeans import pandas as pd Importing company data data = pd.read_csv('companies.csv') Running clustering kmeans = KMeans(n_clusters=5) clusters = kmeans.fit_predict(data[['industry', 'size', 'region']])

[1003] This code allows companies to be classified into clusters.

[1004] Step 3: Simulate the proposal

[1005] The server compares the listed companies with good customers and simulates what proposals would improve customer performance. As input, the server uses information on the listed companies, past transaction history, market trends, and other data. The server runs the simulation using regression analysis and predictive models. As output, it generates proposals.

[1006] Specific behavior:

[1007] The server runs the following Python code to perform the simulation:

[1008] python from sklearn.linear_model import LinearRegression Loading historical transaction data transaction_data = pd.read_csv('transactions.csv') Performing regression analysis model = LinearRegression() model.fit(transaction_data[['feature1', 'feature2']], transaction_data['performance']) Running a prediction predictions = model.predict(new_company_data[['feature1', 'feature2']])

[1009] This code predicts what proposals will be made to new business partners.

[1010] Step 4: Generate a proposal

[1011] The server generates a proposal policy and a proposal based on the simulation results. The simulation results are used as input. The server generates the proposal in natural language using a generative AI model. As output, a proposal is generated.

[1012] Specific behavior:

[1013] The server inputs the following prompt sentence into the generative AI model:

[1014] python prompt = """ Please prepare a proposal for a new business partner. Based on the information below, please include the specific proposal content, its justification, and the expected effects. Industry: IT Size: Medium Region: Tokyo Past transaction history: Yes Market trends: Growing """ response = gpt3.generate(prompt)

[1015] This code will generate a proposal.

[1016] Step 5: Submit your proposal

[1017] The user receives the generated proposal and makes a proposal to the new trading partner. As input, the generated proposal is used. As output, the proposal is provided to the new trading partner.

[1018] Specific behavior:

[1019] The user downloads the proposal generated from the system and submits it to the new business partner.

[1020] (Application example 1)

[1021] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server", and the headset type terminal 314 will be referred to as a "terminal".

[1022] Conventional systems for developing new business partners have difficulty efficiently listing companies with similar attributes to good customers and making appropriate proposals. In addition, generating proposal content requires a lot of manual work, which is time-consuming and labor-intensive. Furthermore, the system is not user-friendly because it does not take into account use on mobile devices such as smartphones and tablets. To solve these problems, a more efficient and effective system for developing new business partners is needed.

[1023] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1024] In this invention, the server includes a means for creating a list of companies in Japan, a means for listing companies with attributes similar to those of good customers and making recommendations using AI, a means for comparing with good customers and simulating what proposals would improve customer performance, a means for generating a proposal policy and a proposal document using AI, a means for simulating proposal contents for new business partners, a means for automatically generating a proposal document using a generation AI model, and a means including an application to be installed on a smartphone or tablet. This makes it possible to efficiently and effectively develop new business partners and quickly generate proposal contents.

[1025] The "domestic company list" is a list that collects basic information about companies located in the country and stores it in a database.

[1026] A "good customer" is a customer who is deemed to be of particularly high transaction value based on past transaction history and business performance.

[1027] "Attribute companies" are companies that have specific attributes such as industry, size, or region.

[1028] "AI recommendation means" is a function that uses artificial intelligence to recommend companies based on specific conditions.

[1029] A "means of simulation" is a function that predicts future results based on past data and market trends.

[1030] The "proposal policy" indicates the basic direction and strategy of the proposal content.

[1031] A "proposal" is a document that describes the specific proposal content, its reasons, and the expected effects.

[1032] A "new business partner" is a new business partner with whom we have not had any transactions until now.

[1033] A "generative AI model" is a model that is trained using artificial intelligence to perform a specific task.

[1034] A "prompt sentence" is an instruction sentence input to a generative AI model.

[1035] An "application installed on a smartphone or tablet" is software that runs on a mobile device.

[1036] A system for implementing the present invention uses a server, a mobile device such as a smartphone or tablet, and a generative AI model. The specific configuration and operation of the system are described below.

[1037] System Configuration

[1038] 1. Server

[1039] The server creates a list of companies in Japan and stores it in a database. The server also runs an AI model to analyze the attributes of good customers and list companies with similar attributes. In addition, the server simulates proposals to new clients and automatically generates proposals using a generative AI model.

[1040] 2. Mobile Devices

[1041] An application that communicates with the server is installed on a mobile device such as a smartphone or tablet, and provides an interface for the user to view a list of potential business partners and to view proposals.

[1042] Data processing and calculation

[1043] 1. Creating a list of companies

[1044] The server collects information on companies in Japan and creates a database that includes attributes such as industry, size, and region. This data is managed using Pandas.

[1045] 2. Analysis of loyal customer attributes

[1046] The server analyzes the data of good customers using KMeans clustering and classifies them into specific clusters, which makes it possible to identify companies that have similar attributes to good customers.

[1047] 3. Listing new business partners

[1048] The server filters companies that have similar attributes to its best customers and creates a list of new business partners, which is then provided to the user through an application on their mobile device.

[1049] 4. Proposed Simulation

[1050] The server uses RandomForestRegressor to simulate proposals for new trading partners. This simulation is based on past trading history and market trends.

[1051] 5. Proposal Generation

[1052] The server uses the generative AI model to automatically generate a proposal. This proposal includes the specific proposal content, its rationale, and the expected effects. The generative AI model uses the OpenAI API.

[1053] Examples

[1054] For example, for manufacturing company A, we generate the following prompt:

[1055] Company name: Company A

[1056] Industry: Manufacturing

[1057] Scale: 100

[1058] Region: Tokyo

[1059] Generate a proposal.

[1060] When this prompt sentence is input into the generative AI model, the AI ​​generates a specific proposal. For example, it may return a proposal such as, "The introduction of a new manufacturing line is expected to improve efficiency by 20%." In this way, users can make effective proposals to new business partners.

[1061] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1062] Step 1:

[1063] The server collects company information in the country and creates a database with attributes such as industry, size, region, etc. As input, it requires a data source of company information (e.g., a public company database) and as output, it obtains a list of companies in the form of a Pandas data frame. This data is used for subsequent analysis.

[1064] Step 2:

[1065] The server analyzes the data of good customers using KMeans clustering and classifies them into specific clusters. As input, it requires data of good customers (e.g. past transaction history, performance data), and as output, it obtains data of good customers with cluster labels. These cluster labels are used to identify the attributes of good customers.

[1066] Step 3:

[1067] The server filters companies with similar attributes to good customers and creates a list of new business partners. As input, it requires data of good customers with cluster labels and a list of companies in the country, and as output, it obtains a list of new business partners. This list is provided to the user through an application on the mobile device.

[1068] Step 4:

[1069] The server uses RandomForestRegressor to simulate proposals for new trading partners. As input, it requires a list of new trading partners and data on past trading history and market trends. As output, it obtains predictions of proposal contents. These predictions are used to generate proposal documents.

[1070] Step 5:

[1071] The server uses the generative AI model to automatically generate proposals. The inputs required are the predicted results of the proposal content and basic information about the new business partner (e.g. company name, industry, size, region), and the output is a proposal that includes the specific proposal content, its justification, and the expected effects. The generative AI model uses the OpenAI API.

[1072] Step 6:

[1073] A user views a list of new business partners and proposals through an application installed on a smartphone or tablet. As input, a list of new business partners and proposals provided by a server are required, and as output, they are displayed in a format that can be viewed by the user. This application provides an interface for the user to make effective proposals to new business partners.

[1074] Example 2

[1075] Next, a second embodiment of the second form will be described. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal".

[1076] With the conventional system, it was difficult to make specific proposals to potential new business partners based on the success stories of good customers. In addition, it took a lot of time and effort to generate proposals, which made it difficult to conduct efficient sales activities.

[1077] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for creating a list of domestic companies, a means for listing companies with the same attributes as good customers and making recommendations using artificial intelligence, a means for comparing with good customers and simulating using artificial intelligence what proposals would improve customer performance, a means for generating a proposal based on the simulation results, and a means for providing the generated proposal to the user. This makes it possible to efficiently make specific proposals based on the success stories of good customers.

[1078] The "Domestic Company List" is a list that compiles information on companies located in Japan.

[1079] A "good customer" is a customer who has a good track record of transactions in the past and who can be expected to continue doing business with the company.

[1080] "Attribute companies" are companies that share a particular industry, size, or other common characteristics.

[1081] "Artificial intelligence" is a technology that enables computer systems to imitate human intelligence to learn and make inferences.

[1082] A "recommendation" is the suggestion of the best option based on specific criteria.

[1083] "Simulation" refers to the virtual reproduction of a real-world situation and predicting its outcomes.

[1084] A "proposal" is a document that documents a specific proposal and indicates specific actions to a business partner.

[1085] A "user" is someone who uses this system to create proposals and make them to business partners.

[1086] The present invention is a system for efficiently making specific proposals to potential new business partners based on the success stories of good customers. A specific embodiment of this system will be described below.

[1087] The server first creates a list of companies in the country. To do this, a database management system (e.g., MySQL) is used to collect information on companies located in the country. Next, data on good customers is collected and past transaction records and performance data are analyzed. This analysis is performed using Python's Pandas library and NumPy library.

[1088] The server refers to an industry database to list companies with similar attributes to good customers. This allows small and medium-sized enterprises in the same industry to be extracted as potential new business partners. The extracted company list is recommended using artificial intelligence (e.g., generative AI model).

[1089] Next, the server simulates whether a proposal for a potential new business partner will lead to improved business performance based on the success stories of good customers. This simulation uses a generative AI model (e.g. GPT-4). Specific examples of prompt sentences include the following:

[1090] "Our good customer A has improved its performance in the past after receiving the following proposal. Please simulate what kind of effect you can expect if we make a similar proposal to a potential new business partner B."

[1091] Based on the simulation results, the server generates a proposal for the potential new business partner. This proposal describes the specific actions that the potential new business partner should take, their effects, and the services to support those actions. The generative AI model is used again to generate the proposal. Examples of specific prompt sentences include the following:

[1092] "Please prepare a proposal for potential new business partner B. In the proposal, please describe the specific actions that B should take, their effects, and the services we can provide to support those actions."

[1093] The generated proposal is provided to the user via the terminal. The user can make specific proposals to potential new business partners based on this proposal. This makes it possible to efficiently make specific proposals based on the success stories of good customers.

[1094] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1095] Step 1: Data collection

[1096] The server collects company information using a database management system (e.g., MySQL) to create a list of companies in Japan. As input, it obtains basic information about the companies (e.g., company name, location, industry, and size). As output, it generates a list of companies in Japan. Specifically, the server executes SQL queries to extract the required information from the database.

[1097] Step 2: Analyze your loyal customer data

[1098] The server collects and analyzes past transaction data and performance data of good customers. As input, it obtains transaction history and performance data of good customers. As output, it identifies successful proposals and factors that improved performance. Specifically, the server uses Python's Pandas library to analyze the data and extract success stories.

[1099] Step 3: List potential new business partners

[1100] The server refers to an industry database to list companies that have similar attributes as good customers. As input, it retrieves company information from the industry database. As output, it generates a list of potential new business partners. Specifically, the server executes an SQL query to extract companies that match the criteria.

[1101] Step 4: Simulation

[1102] The server simulates whether proposals for potential new business partners will lead to improved business performance, based on success stories of good customers. As input, it inputs the success stories of good customers and information on potential new business partners into the generative AI model. As output, it obtains the simulation results. In concrete terms, the server inputs the following prompt sentence into the generative AI model (e.g. GPT-4):

[1103] "Our good customer A has improved its performance in the past after receiving the following proposal. Please simulate what kind of effect you can expect if we make a similar proposal to a potential new business partner B."

[1104] Step 5: Generate a proposal

[1105] The server generates a proposal for a potential new business partner based on the simulation results. As input, it inputs the simulation results and information on the potential new business partner into the generative AI model. As output, a proposal is generated. Specifically, the server inputs the following prompt sentence into the generative AI model:

[1106] "Please prepare a proposal for potential new business partner B. In the proposal, please describe the specific actions that B should take, their effects, and the services we can provide to support those actions."

[1107] Step 6: Submit your proposal

[1108] The server sends the generated proposal to the terminal. As input, the server obtains the generated proposal. As output, the proposal is provided to the user. As a specific operation, the server sends the proposal to the terminal, and the terminal displays the proposal so that the user can confirm it. The user can make a specific proposal to a potential new business partner based on this proposal.

[1109] (Application example 2)

[1110] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server", and the headset type terminal 314 will be referred to as a "terminal".

[1111] With conventional systems, it was difficult to make effective proposals to potential new business partners based on the success stories of good customers. In addition, there was a problem that efficient sales activities could not be carried out because it took a lot of time and effort to generate proposals. Furthermore, the content of the proposals sometimes lacked consistency, which could reduce the trust of potential new business partners. In order to solve these issues, there is a need for a system that can generate prompt sentences based on the success stories of good customers and automatically generate effective proposals using AI.

[1112] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1113] In this invention, the server includes a means for creating a list of companies in Japan, a means for listing companies with attributes similar to those of good customers and making recommendations using AI, a means for comparing with good customers and simulating what proposals would improve customer performance, a means for AI to generate a proposal policy and a proposal, a means for generating a prompt sentence based on success stories of good customers, a means for generating a proposal based on the generated prompt sentence, and a means for outputting a proposal for a new business partner candidate. This makes it possible to automatically generate effective proposals based on success stories of good customers quickly and consistently.

[1114] A "means for creating a domestic company list" is a method or device for collecting information on companies existing in the country and organizing it in list form.

[1115] "Means for compiling a list of companies with similar attributes to good customers and recommending them using AI" refers to a method or device for identifying companies that have similar characteristics to good customers and recommending these companies using artificial intelligence.

[1116] "A means of using AI to simulate what proposals will improve customer performance by comparing with good customers" refers to a method or device that compares data on good customers with data on potential new business partners and uses artificial intelligence to predict what kind of proposals will contribute to improving performance.

[1117] "Means for AI-generated proposal guidelines and written proposals" refers to methods or devices for automatically creating proposal guidelines and specific written proposals using artificial intelligence.

[1118] A "means for generating prompt sentences based on success stories of good customers" refers to a method or device for creating instruction sentences (prompt sentences) for artificial intelligence based on past success stories of good customers.

[1119] The "means for generating a proposal based on the generated prompt sentence" refers to a method or device for an artificial intelligence to automatically create a proposal using the generated prompt sentence as input.

[1120] The "means for outputting a proposal to a new supplier candidate" refers to a method or device for presenting the generated proposal to the new supplier candidate.

[1121] An embodiment of the present invention will now be described. First, the system uses the following hardware and software.

[1122] Hardware and Software Used

[1123] Hardware: Servers, smartphones

[1124] Software: Python, OpenAI API, Pandas

[1125] System Configuration

[1126] The server includes the following means:

[1127] 1. Means for creating a list of domestic companies: The server collects information on companies existing in the country and organizes it in the form of a list. This list includes basic information, business performance data, industry, etc. of the companies.

[1128] 2. Compiling a list of companies with similar attributes to those of best customers and using AI to recommend them: The server identifies companies with similar characteristics based on data on best customers and uses artificial intelligence to recommend these companies.

[1129] 3. A means of using AI to simulate what proposals would improve customer performance by comparing with best customers: The server compares data on best customers with data on potential new business partners, and uses artificial intelligence to predict what kind of proposals would contribute to improving performance.

[1130] 4. Means for AI to generate proposal guidelines and written proposals: The server uses artificial intelligence to automatically create proposal guidelines and specific written proposals.

[1131] 5. Means for generating prompt sentences based on success stories of good customers: The server creates instructions (prompt sentences) for the artificial intelligence based on past success stories of good customers.

[1132] 6. Means for generating a proposal based on the generated prompt sentence: The server uses the generated prompt sentence as input and the artificial intelligence automatically creates a proposal.

[1133] 7. Means for outputting a proposal to a potential new business partner: The server presents the generated proposal to the potential new business partner.

[1134] Data processing and calculation

[1135] The server collects data on good customers and potential new business partners, compares and analyzes this data, and uses Python and Pandas to read the data and OpenAI API to perform simulations and generate proposals using artificial intelligence.

[1136] Examples

[1137] For example, if a good customer is a "major IT company" that has been successful in the past when "SEO optimization and content marketing" was proposed to them, they can use that success story to make a similar proposal to a potential new business partner, a "small and medium-sized IT company."

[1138] Examples of prompt statements A valued client (a large IT company) saw an improvement in their business performance after receiving the following recommendations: SEO optimization and content marketing. Run a simulation to see if a similar recommendation would be effective for a potential new business partner (a small or medium-sized IT company).

[1139] In this way, the server can quickly and consistently automatically generate effective proposals based on best customer success stories.

[1140] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1141] Step 1:

[1142] The server creates a list of companies in Japan. Specifically, it collects basic information, performance data, industry, etc. of companies and organizes them in list form. As input, it uses company databases and publicly available company information, and as output, it generates an organized company list.

[1143] Step 2:

[1144] The server creates a list of companies with similar attributes to good customers and uses AI to make recommendations. Specifically, it identifies companies with similar characteristics based on the data of good customers and uses artificial intelligence to recommend these companies. It uses the data of good customers and the company list as input, and generates a list of recommended companies as output.

[1145] Step 3:

[1146] The server compares the data of good customers with those of potential new business partners and uses AI to simulate what proposals would improve the customer's performance. Specifically, it compares the data of good customers with that of potential new business partners and uses artificial intelligence to predict what proposals would contribute to improving performance. The server uses the data of good customers and the data of potential new business partners as input and generates the simulation results as output.

[1147] Step 4:

[1148] The server uses AI to generate the proposal policy and proposal document. Specifically, it uses artificial intelligence to automatically create the proposal policy and specific proposal document. It uses the simulation results as input and generates the proposal policy and proposal document as output.

[1149] Step 5:

[1150] The server generates a prompt sentence based on the success stories of good customers. Specifically, it creates an instruction sentence (prompt sentence) for the artificial intelligence based on the past success stories of good customers. The success story data of good customers is used as input, and the prompt sentence is generated as output.

[1151] Step 6:

[1152] The server generates a proposal based on the generated prompt. Specifically, the AI ​​automatically creates a proposal using the generated prompt as input. The server uses the prompt as input and generates a proposal as output.

[1153] Step 7:

[1154] The server outputs a proposal to the new supplier candidate. Specifically, the server presents the generated proposal to the new supplier candidate. The server uses the generated proposal as input, and generates a proposal to be presented to the new supplier candidate as output.

[1155] In addition, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1156] "Example 1"

[1157] In one embodiment of the present invention, the AI ​​includes an emotion engine that recognizes the user's emotions. The emotion engine reads emotions from the user's tone of voice, facial expressions, choice of words, etc. For example, if the user is happy or excited, the emotion engine conveys that information to the AI. The AI ​​adjusts the suggestions based on that information. Specifically, if the user is happy, the AI ​​makes suggestions to amplify that happiness. Also, if the user is frustrated or angry, the AI ​​makes suggestions to resolve that frustration.

[1158] "Example 2"

[1159] In another embodiment of the present invention, the emotion engine recognizes the user's emotion and optimizes the suggestions based on the emotion. Specifically, if the user feels happy, the AI ​​makes suggestions to amplify the joy. Also, if the user feels frustrated or angry, the AI ​​makes suggestions to resolve the frustration. This optimization is achieved by learning the correlation between the user's emotion and the suggestions. For example, the AI ​​analyzes past suggestions and the user's response to learn what suggestions will amplify the user's joy and what suggestions will resolve the user's frustration.

[1160] The process flow of each embodiment will be described below.

[1161] "Example 1"

[1162] Step 1: User interaction begins, either by the user asking the system a question or by the system providing information to the user.

[1163] Step 2: The emotion engine reads the user's emotions from their tone of voice, facial expressions, choice of words, etc.

[1164] Step 3: The emotion engine communicates the emotional information it has read to the AI.

[1165] Step 4: The AI ​​adjusts the suggestions based on the emotion information. Specifically, if the user is feeling happy, the AI ​​will make suggestions to amplify that happiness. Also, if the user is feeling dissatisfied or angry, the AI ​​will make suggestions to alleviate that dissatisfaction.

[1166] "Example 2"

[1167] Step 1: User interaction begins, either by the user asking the system a question or by the system providing information to the user.

[1168] Step 2: The emotion engine reads the user's emotions from their tone of voice, facial expressions, choice of words, etc.

[1169] Step 3: The emotion engine communicates the emotional information it has read to the AI.

[1170] Step 4: The AI ​​optimizes the content of the suggestions based on the emotion information. Specifically, if the user is feeling happy, the AI ​​will make suggestions to amplify that happiness. Also, if the user is feeling dissatisfied or angry, the AI ​​will make suggestions to alleviate that dissatisfaction.

[1171] Step 5: The AI ​​analyzes past suggestions and user responses to learn which suggestions will increase user delight and which suggestions will eliminate user dissatisfaction.

[1172] Example 1

[1173] Next, a description will be given of Example 1 of the embodiment 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal".

[1174] In conventional new business partner development systems, the creation of company lists, attribute analysis of good customers, and generation of proposal content are often done manually, which is inefficient. In addition, the proposal content cannot be adjusted to take the user's feelings into account, which limits the effectiveness of the proposal. This creates the problem that companies are unable to fully improve their performance or develop new business partners.

[1175] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1176] In this invention, the server includes a means for creating a list of companies in Japan, a means for listing companies with attributes similar to those of good customers and making recommendations using artificial intelligence, a means for comparing with good customers and simulating using artificial intelligence what proposals would improve customer performance, a means for generating a proposal policy and a proposal document using artificial intelligence, and a means for adjusting the proposal contents using an emotion engine that recognizes the user's emotions. This makes it possible to efficiently create a list of companies, analyze the attributes of good customers, automatically generate proposal contents, and adjust the proposal contents according to the user's emotions.

[1177] A "domestic company list" is a list that collects information on companies that exist in Japan.

[1178] A "good customer" is a customer who has a good track record of transactions and business performance in the past.

[1179] "Attribute companies" refer to companies that are classified based on specific conditions (industry, size, region, etc.).

[1180] "Artificial intelligence" is a technology that uses machine learning and data analysis to mimic human intelligence.

[1181] A "recommendation" is the suggestion of the best option based on specific criteria.

[1182] "Simulation" refers to modeling real-world situations and conducting virtual experiments and predictions.

[1183] A "proposal" is a document that describes a specific proposal, its rationale, and the expected results.

[1184] The "emotion engine" is a technology that reads emotions from a user's tone of voice, facial expressions, choice of words, etc.

[1185] "Recommendations" refers to recommended actions or strategies for achieving a particular objective.

[1186] This invention is a system for developing new business partners using AI, which creates a list of companies in Japan and then selects from that list those with similar attributes to good customers. The system uses AI to perform analysis, taking into account attributes such as the company's industry, size, and region. Next, the AI ​​compares the company with good customers and simulates what proposals would improve the customer's performance. This simulation is performed based on past transaction history and market trends. Finally, the AI ​​generates a proposal policy and document based on the results. This proposal document includes the specific proposal content, its reasons, and expected effects.

[1187] Hardware and Software Used

[1188] Hardware: Servers, terminals

[1189] Software: AI models (e.g. TensorFlow, PyTorch), emotion engines (e.g. Affectiva, Microsoft Azure Emotion API)

[1190] Specific operation of the system

[1191] 1. Creating a list of companies:

[1192] The server extracts company information from a national company database.

[1193] The terminal provides an interface for inputting user-specified conditions (industry type, size, region, etc.).

[1194] The user inputs the conditions through a terminal.

[1195] The server uses an AI model to filter the list of companies based on the specified criteria.

[1196] The server transmits the filtering result to the terminal.

[1197] The terminal displays the filtering results to the user.

[1198] 2. Attribute analysis of loyal customers:

[1199] The server collects data on loyal customers.

[1200] The terminal provides an interface for inputting information on preferred customers provided by the user.

[1201] The user inputs information about good customers through the terminal.

[1202] The server uses an AI model to analyze attributes of good customers, such as industry, size, and region.

[1203] Based on the analysis results, the server compiles a list of similar companies.

[1204] The server transmits the list result to the terminal.

[1205] The terminal displays the listing results to the user.

[1206] 3. Proposed simulation:

[1207] The server collects past trading history and market trend data.

[1208] The server uses an AI model to simulate what proposals would improve customer performance.

[1209] The server transmits the simulation results to the terminal.

[1210] The terminal displays the simulation results to the user.

[1211] 4. Proposal Generation:

[1212] The server decides on a proposal policy based on the simulation results.

[1213] The server uses the AI ​​model to generate a proposal that includes specific proposal details, their rationale, and expected benefits.

[1214] The server transmits the generated proposal to the terminal.

[1215] The terminal displays the proposal to the user.

[1216] 5. Using the Emotion Engine:

[1217] The device uses an emotion engine to analyze the user's tone of voice, facial expressions, choice of words, etc.

[1218] The emotion engine sends the analysis results to the server.

[1219] The server uses an AI model to tailor its suggestions based on the user's emotions.

[1220] The server sends the adjusted proposal to the terminal.

[1221] The device displays the proposed adjustments to the user.

[1222] Examples and prompts

[1223] Examples:

[1224] If a user is looking to develop new business partners, the system will list companies from a list of domestic companies based on the following criteria: industry (manufacturing), size (small and medium-sized enterprises), and region (Kanto region).

[1225] Designate "A Co., Ltd." as a valued customer and list similar companies based on its attributes.

[1226] Based on past transaction history and market trends, the system suggests "introducing product B," citing as its justification that "sales increased by 20% in past implementation cases."

[1227] When the user is reviewing the proposal, the emotion engine reads the "excitement" from the user's facial expression and further emphasizes the proposal.

[1228] Example prompt: In order to develop new business partners, please make a list of companies from a list of domestic companies with the following criteria: industry (manufacturing), size (small and medium-sized enterprises), and region (Kanto region). Specify "Corporation A" as a good customer, and make a list of similar companies based on that attribute. Based on past transaction history and market trends, simulate what proposals would improve the customer's performance, and generate a proposal that includes specific proposal content, its reasons, and the expected effects.

[1229] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1230] Step 1:

[1231] Creating a company list

[1232] Input: The user enters conditions such as industry, size, and region into the terminal.

[1233] Specific operation: The terminal receives the conditions specified by the user and sends them to the server.

[1234] Data processing: The server extracts company information that matches the specified conditions from the company database.

[1235] Output: The server generates the filtered list of companies and sends it to the terminal.

[1236] Specific operation: The terminal displays the filtering results to the user in list form.

[1237] Step 2:

[1238] Attribute analysis of loyal customers

[1239] Input: The user enters preferred customer information into the terminal.

[1240] Specific operation: The terminal receives the information on good customers provided by the user and transmits it to the server.

[1241] Data processing: The server collects data on good customers and uses an AI model to analyze attributes such as industry, size, and region.

[1242] Output: Based on the analysis results, the server creates a list of similar companies and sends it to the terminal.

[1243] Specific behavior: The terminal displays the listing results to the user.

[1244] Step 3:

[1245] Proposal Simulation

[1246] Input: The server collects historical trading and market trend data.

[1247] What happens: The server inputs this data into the AI ​​model.

[1248] Data calculation: The AI ​​model simulates what recommendations would improve customer performance.

[1249] Output: The server generates the simulation results and sends them to the terminal.

[1250] Specific operation: The terminal displays the simulation results to the user.

[1251] Step 4:

[1252] Proposal Generation

[1253] Input: The server receives the simulation results.

[1254] Specific operation: The server uses the AI ​​model to generate a proposal that includes specific proposal content, its rationale, and the expected effects.

[1255] Data processing: Format the proposal content and put it into document format.

[1256] Output: The server sends the generated proposal to the terminal.

[1257] Specific behavior: The device displays the proposal to the user.

[1258] Step 5:

[1259] Using the Emotion Engine

[1260] Input: The device collects the user's tone of voice, facial expressions, word choice, etc.

[1261] Specific operation: The device inputs the collected data into the emotion engine.

[1262] Data calculation: The emotion engine analyzes the user's emotion and sends the result to the server.

[1263] Output: The server receives the sentiment analysis results and uses the AI ​​model to refine the suggestions.

[1264] Specific operation: The server sends the adjusted proposal to the device, which then displays it to the user.

[1265] (Application example 1)

[1266] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server", and the headset type terminal 314 will be referred to as a "terminal".

[1267] Conventional systems for developing new business partners can create company lists and generate proposals, but they do not adjust the content of the proposals to take into account the user's feelings, which means that the effectiveness of the proposals is limited. In addition, there is a lack of systems that utilize mobile devices such as smartphones, which also creates a problem of low user convenience.

[1268] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1269] In this invention, the server includes a means for creating a list of companies in Japan, a means for listing companies with attributes similar to those of good customers and making recommendations using AI, a means for comparing with good customers and simulating with AI what proposals would improve customer performance, a means for AI to generate a proposal policy and proposal, a means for adjusting the proposal content using an emotion engine that recognizes the user's emotions, and a means including an application to be installed on a smartphone. This enables effective proposals that take the user's emotions into consideration, and realizes a highly convenient system that utilizes smartphones.

[1270] The "company list" is a database that compiles domestic companies in a list format, and includes attribute information such as the company's industry, size, and region.

[1271] A "good customer" is one who is particularly valuable based on past transaction history and business performance.

[1272] "Attribute companies" refer to companies that have similar attributes, such as industry, size, and region, as good customers.

[1273] "Recommendation" means that AI performs analysis and suggests the best options based on certain conditions.

[1274] "Simulation" means that AI predicts what results a particular proposal will bring, based on past data and market trends.

[1275] A "proposal" is a document generated by AI that includes the specific proposal content, its rationale, expected effects, etc.

[1276] The "emotion engine" is a system that reads emotions from the user's tone of voice, facial expressions, choice of words, etc., and conveys that information to the AI.

[1277] A "smartphone" is a type of mobile phone, a multi-function device that can connect to the Internet and install applications.

[1278] An "application" is software installed on a smartphone that provides specific functions or services.

[1279] The following system configuration will be described as an embodiment of the present invention.

[1280] System Configuration

[1281] Hardware

[1282] Server: Manages the database, runs the AI ​​models, and processes the emotion engine.

[1283] Smartphone: Functions as a user interface and recognizes the user's emotions using a camera and microphone.

[1284] software

[1285] Database: Stores a list of companies within the country and manages data to create a list of companies with similar attributes to good customers.

[1286] AI model: A generative AI model that suggests products based on a user's purchasing history and browsing history.

[1287] Emotion engine: Software that detects emotions from a user's tone of voice, facial expressions, choice of words, etc.

[1288] Application: An application that is installed on a smartphone and allows the user to interact with it.

[1289] Data processing and calculation

[1290] server

[1291] The server first creates a list of companies in Japan, listing companies with attributes similar to those of good customers. It then uses an AI model to compare these companies with good customers and simulate what proposals would improve their performance. It also uses an emotion engine to recognize the user's emotions and adjusts the content of the proposals based on that information. Finally, it generates a proposed policy and proposal document and sends them to the smartphone.

[1292] Smartphone

[1293] The smartphone collects the user's purchase history and browsing history and sends them to the server. It also uses a camera and microphone to analyze the user's facial expressions and tone of voice and sends them to the emotion engine. The proposals received from the server are displayed to the user and an interaction takes place.

[1294] Examples

[1295] For example, when a user uses a smartphone to access an online shopping site, their purchase history and browsing history are sent to the server. Based on this data, the server uses an AI model to suggest new products. In addition, the smartphone's camera and microphone are used to recognize the user's emotions, and the emotion engine sends this information to the server. The server adjusts the suggestions based on the emotion information, suggesting additional special offer products if the user is happy, and suggesting products that will calm the user if the user is angry.

[1296] Examples of prompt statements Recommend new products based on the user's purchase and browsing history. Recognize the user's emotions and adjust the suggestions accordingly. For example, if the user is happy, add special offer products, if the user is angry, suggest products that will calm them down.

[1297] In this way, it becomes possible to make effective suggestions that take the user's emotions into account, and a highly convenient system that utilizes smartphones can be realized.

[1298] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1299] Step 1:

[1300] The server creates a list of companies in Japan. As input, it obtains attribute information such as the company's industry, size, and region from the database, and generates a company list based on this information. As output, it obtains a company list.

[1301] Step 2:

[1302] The server lists companies with the same attributes as good customers. The attribute information of good customers and the company list are used as input. Data processing involves filtering and listing companies that match the attributes of good customers. The list of companies with attributes is obtained as output.

[1303] Step 3:

[1304] The server uses the AI ​​model to compare the customer with good customers and simulate what proposals would improve the customer's performance. The input is the trading history and market trend data of good customers. As a data calculation, the AI ​​model analyzes this data and predicts the optimal proposal content. The proposal content is obtained as the output.

[1305] Step 4:

[1306] The server uses an emotion engine to recognize the user's emotions. As input, it uses facial expression images and voice data of the user sent from the smartphone. As data processing, the emotion engine analyzes these data and identifies the user's emotions. As output, emotion information is obtained.

[1307] Step 5:

[1308] The server adjusts the proposal content based on the emotion information. As input, it uses the proposal content obtained in step 3 and the emotion information obtained in step 4. As data calculation, it changes the proposal content according to the emotion information. For example, if the user is happy, it adds a special offer product, and if the user is angry, it suggests a product that calms the mood. As output, it obtains the adjusted proposal content.

[1309] Step 6:

[1310] The server generates a proposal policy and a proposal document and sends it to the smartphone. The adjusted proposal content is used as input. As data processing, the proposal content is converted into a document format and a proposal document is generated. As output, the proposal document is obtained and sent to the smartphone.

[1311] Step 7:

[1312] The smartphone displays the proposal received from the server to the user. As an input, the smartphone uses the proposal sent from the server. As a specific operation, the smartphone displays the proposal on the screen so that the user can view it. As an output, the user can confirm the contents of the proposal.

[1313] Step 8:

[1314] The user uses a smartphone to provide feedback on the proposal contents. As an input, the user inputs feedback based on the contents of the proposal. As a specific operation, the user inputs feedback through the smartphone interface and transmits it to the server. As an output, feedback data is obtained.

[1315] Step 9:

[1316] The server receives feedback from the user and reflects it in the next proposal. As input, it uses the user's feedback data. As data calculation, it analyzes the feedback data and uses it as learning data for the AI ​​model. As output, it obtains improved proposal content.

[1317] Example 2

[1318] Next, a second embodiment of the second form will be described. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal".

[1319] In the conventional system, it was difficult to make effective proposals when applying success stories of good customers to potential new business partners. In addition, the content of the proposals was not optimized to take into account the user's feelings, so the acceptability and effectiveness of the proposals was limited. This led to the issue that the business performance of potential new business partners was not improved sufficiently and new business development was not achieved.

[1320] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1321] In this invention, the server includes a means for creating a list of companies in Japan, a means for listing companies with attributes similar to those of good customers and making recommendations using a generative AI model, a means for comparing with good customers and simulating what proposals would improve customer performance using a generative AI model, a means for the generative AI model to generate a proposal policy and a proposal document, and an emotion engine that recognizes the user's emotions and optimizes the proposal content based on the emotions. This makes it possible to effectively apply success stories of good customers to new business partner candidates and make optimal proposals according to the user's emotions.

[1322] A "domestic company list" is a compilation in list form of information on companies located in Japan.

[1323] A "good customer" refers to a customer company that has a good track record of transactions in the past and has stable business performance.

[1324] "Attribute companies" refers to a group of companies that share a particular industry, size, or other characteristic.

[1325] A "generative AI model" refers to an algorithm or program that uses artificial intelligence technology to analyze data and make optimal suggestions and simulations.

[1326] "Recommending" refers to presenting the best options or suggestions based on specific criteria.

[1327] "Simulation" refers to virtually recreating a real-world situation and predicting the outcome.

[1328] "Proposal policy" refers to the basic direction and strategy of the proposal content.

[1329] A "proposal" is a written summary of the proposal content, which includes a specific action plan and its effects.

[1330] An "emotion engine" refers to technology or a program that analyzes a user's emotions and generates optimal suggestions based on those emotions.

[1331] The present invention is a system for making proposals to potential new business partners based on success stories of good customers, and optimizing the content of the proposals based on the user's emotions. A specific embodiment of this system will be described below.

[1332] Hardware and Software Used

[1333] Hardware: Servers, terminals

[1334] Software: Generative AI models, emotion engine, database management system (DBMS)

[1335] Data collection

[1336] The server uses a database management system (DBMS) to collect performance data and past proposal data of good customers. The terminal collects the user's emotion data through an emotion engine. The emotion engine analyzes the user's emotions from their facial expressions and voice.

[1337] Data analysis

[1338] The server uses the collected data to analyze what kind of proposals good customers received that improved their performance. This analysis is performed using a generative AI model. The generative AI model learns from past proposals and performance data, and simulates proposal content for potential new business partners.

[1339] Proposal generation

[1340] The server generates a proposal for potential new business partners based on the simulation results, which describes specific actions, their effects, and the services that will be supported.

[1341] Emotional Optimization

[1342] The emotion engine recognizes the user's emotions and optimizes the content of suggestions based on those emotions. For example, if the user is feeling happy, the emotion engine will make suggestions that will amplify that happiness. Conversely, if the user is feeling dissatisfied or angry, the emotion engine will make suggestions that will alleviate that dissatisfaction.

[1343] Examples

[1344] Valued customers: Major companies in the IT industry

[1345] Potential new business partners: Small and medium-sized businesses in the IT industry

[1346] Proposal content: Based on past proposals received from valued customers, we simulate how to improve the performance of potential new business partners and document a specific action plan in the proposal.

[1347] Examples of prompt statements If your best customers are large companies in the IT industry, list small and medium-sized companies in the same industry as potential new business partners. Based on what proposals your best customers received in the past that improved their performance, use AI to simulate whether a similar proposal would lead to improved performance for potential new business partners, and generate a proposal based on the results. Also, recognize the user's emotions and optimize the content of the proposal based on those emotions.

[1348] This system can effectively apply the success stories of good customers to potential new business partners and make optimal proposals based on the user's emotions, thereby helping to improve the business performance of potential new business partners and develop new business.

[1349] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1350] Step 1:

[1351] Data collection

[1352] The server uses a database management system (DBMS) to collect performance data and past proposal data of good customers. Specifically, the server executes an SQL query to retrieve required data from the database. The input is identification information of good customers, and the output is performance data and past proposal data of good customers. The terminal collects user emotion data through an emotion engine. Specifically, the terminal uses a camera and microphone to capture the user's facial expressions and voice, and transmits them to the emotion engine. The input is the user's real-time facial expression and voice data, and the output is analyzed emotion data.

[1353] Step 2:

[1354] Data analysis

[1355] Based on the collected data, the server analyzes what kind of proposals good customers received that improved their performance. A generative AI model is used for this analysis. Specifically, the server inputs data into the generative AI model, which then simulates the proposal content. The input is the performance data and past proposal data of good customers, and the output is the optimal proposal content as a result of the simulation. The generative AI model uses a neural network to analyze the data and generate the optimal proposal content.

[1356] Step 3:

[1357] Proposal generation

[1358] The server generates proposals for potential new business partners based on the simulation results. Specifically, the server embeds data in a proposal template based on the simulation results obtained from the generative AI model. The input is the optimal proposal content as a result of the simulation, and the output is the generated proposal. The proposal is generated in PDF or Word format and sent to the terminal.

[1359] Step 4:

[1360] Emotional Optimization

[1361] The emotion engine recognizes the user's emotion and optimizes the suggestions based on the emotion. Specifically, the emotion engine analyzes the user's emotion data and determines the emotional state. The input is the user's emotion data and the output is the determined emotional state. The server adjusts the suggestions based on the emotional state obtained from the emotion engine. The input is the determined emotional state and the output is optimized suggestions.

[1362] In this way, the system can effectively apply success stories of good customers to potential new business partners and make optimal proposals based on the user's emotions.

[1363] (Application example 2)

[1364] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server", and the headset type terminal 314 will be referred to as a "terminal".

[1365] Conventional corporate proposal systems can make proposals to potential new business partners based on data on good customers, but they have the problem of being unable to make optimal proposals that take customer emotions into account. In addition, there was a lack of means to analyze customer emotions in real time and optimize proposal content based on that, making it difficult to increase customer satisfaction. Furthermore, there was no established method for effectively using prompt sentences when generating proposals using a generative AI model.

[1366] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1367] In this invention, the server includes a means for creating a list of companies in Japan, a means for listing companies with attributes similar to those of good customers and making recommendations using AI, a means for comparing with good customers and simulating with AI what proposals would improve customer performance, a means for generating a proposal policy and a proposal using AI, a means for recognizing customer emotions and optimizing the proposal content based on the emotions, a means for analyzing customer emotions in real time using a smart device, a means for generating a proposal using a generative AI model, and a means for generating a proposal using a prompt sentence. This makes it possible to make optimal proposals in real time that take into account customer emotions, thereby increasing customer satisfaction.

[1368] The "Domestic Company List" is a list that compiles information on companies located in Japan.

[1369] A "good customer" is a customer who is particularly valuable to a company and who does business with the company on an ongoing basis.

[1370] "Attribute companies" are a group of companies that share certain characteristics or conditions.

[1371] "AI recommendation" means using artificial intelligence to recommend specific companies or products.

[1372] "Simulation" means to virtually reproduce a real-world situation and make predictions and analyses.

[1373] A "proposal policy" is the basic direction or strategy of a proposal or plan.

[1374] A "proposal" is a document summarizing the contents of a specific proposal.

[1375] "Recognizing customer emotions" means analyzing the customer's emotions from their facial expressions, tone of voice, etc.

[1376] "Optimizing the proposal" means adjusting the proposal to best suit specific conditions or circumstances.

[1377] A "smart device" is an electronic device with Internet connectivity and advanced computing capabilities.

[1378] "Analyzing in real time" means processing data instantly and obtaining results.

[1379] A "generative AI model" is a model that is trained using artificial intelligence to perform a specific task.

[1380] A "prompt" is an instruction given to a generative AI model to obtain a particular output.

[1381] A system for carrying out the present invention has the following configuration: The server includes means for creating a list of companies in Japan, means for listing companies with similar attributes to good customers and using AI to recommend them, means for comparing with good customers and using AI to simulate what proposals would improve customer performance, means for AI to generate proposal guidelines and proposals, means for recognizing customer emotions and optimizing proposal content based on those emotions, means for analyzing customer emotions in real time using a smart device, means for generating proposals using a generative AI model, and means for generating proposals using prompt sentences.

[1382] Program processing explanation

[1383] The server first creates a list of companies in Japan. It then lists companies with similar attributes to good customers and uses artificial intelligence (AI) to recommend these companies. It compares the data with good customers and uses the AI ​​to simulate what proposals would improve the performance of potential new business partners. Based on the results of this simulation, the AI ​​generates a proposed policy and proposal document.

[1384] In addition, the server analyzes customer emotions in real time using smart devices (e.g. smart glasses). The smart device's camera and microphone are used to capture the customer's facial expressions and tone of voice. This data is analyzed using an emotion engine such as Microsoft Azure Cognitive Services. Based on the customer's emotions obtained as a result of the analysis, the content of the proposal is optimized.

[1385] When generating a proposal using a generative AI model (e.g. GPT-3), a prompt sentence is used. A prompt sentence is an instruction sentence input to the generative AI model to obtain a specific output. For example, the following prompt sentence is used.

[1386] Examples of prompt statements Customer Sentiments: Delight Customer Data: Data of loyal customers Proposal: Example

[1387] For example, when a customer is looking at a product through smart glasses in a brick-and-mortar store, a camera captures the customer's facial expression and recognizes "happiness" using the Azure Face API. The server uses GPT-3 to generate a proposal based on this emotion data and data on loyal customers. The generated proposal contains specific actions such as "If you purchase this product, you will receive an additional 10% off coupon."

[1388] In this way, it becomes possible to make optimal proposals in real time that take into account the customer's feelings, thereby increasing customer satisfaction.

[1389] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1390] Step 1:

[1391] The server creates a list of companies in Japan. As input, it obtains company information from a company database and processes it into a list format. As output, a list of companies in Japan is generated.

[1392] Step 2:

[1393] The server lists companies with similar attributes to good customers and uses AI to make recommendations. As input, it uses attribute data of good customers and a list of companies in Japan. The AI ​​analyzes this data and lists companies with matching attributes. As output, a list of recommended companies is generated.

[1394] Step 3:

[1395] The server compares the data with that of good customers and uses AI to simulate what proposals would improve the performance of potential new business partners. The performance data of good customers and the list of recommended companies are used as input. The AI ​​runs a simulation based on this data and generates optimal proposals. The simulation results are obtained as output.

[1396] Step 4:

[1397] The server uses the simulation results as input to generate a proposal policy and a proposal document using AI. The simulation results are used as input. Based on this, the AI ​​generates a specific proposal policy and proposal document. As output, a proposal policy and proposal document are generated.

[1398] Step 5:

[1399] The terminal (smart device) analyzes the customer's emotions in real time. As input, it uses facial and voice data of the customer acquired from the camera and microphone installed in the smart device. This data is analyzed by an emotion engine such as Microsoft Azure Cognitive Services. As output, it obtains the customer's emotion data.

[1400] Step 6:

[1401] The server optimizes the proposal content based on the customer's emotional data. As input, it uses the customer's emotional data, the proposal policy, and the proposal document. The AI ​​analyzes these data and adjusts the proposal content to the optimal content according to the emotion. As output, an optimized proposal document is generated.

[1402] Step 7:

[1403] The server uses the prompt to generate a proposal using a generative AI model (e.g. GPT-3). As input, it uses the prompt and the optimized proposal content. The generative AI model uses these data to generate the final proposal. As output, it obtains the completed proposal.

[1404] Examples of prompt statements Customer Sentiments: Delight Customer Data: Data of loyal customers Proposal:

[1405] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1406] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1407] Another example of generative AI is Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1408] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1409] [Fourth embodiment]

[1410] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1411] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1412] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[1413] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1414] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[1415] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[1416] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[1417] The control target 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, legs, etc. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, legs, etc. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1418] Fig. 8 shows an example of main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1419] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1420] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1421] In the robot 414, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1422] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1423] "Example 1"

[1424] One embodiment of the present invention is a system for developing new business partners using AI. This system creates a list of companies in Japan, and from that list, makes a list of companies that have similar attributes to good customers. The AI ​​performs analysis to make the list, taking into consideration attributes such as the company's industry, size, and region. Next, the AI ​​compares the company with good customers and simulates what proposals would improve the customer's performance. This simulation is performed based on past transaction history and market trends. Finally, the AI ​​generates a proposal plan and a proposal document based on the results. This proposal document includes the specific proposal content, its reasons, expected effects, etc.

[1425] "Example 2"

[1426] As a specific example, if a good customer is a major company in the IT industry,

[1427] The AI ​​then lists businesses as potential new business partners. Based on what proposals good customers received in the past that improved their performance, the AI ​​runs a simulation to see whether a similar proposal would lead to improved business performance for the new business partner candidate. Based on the results, the AI ​​generates a proposal for the new business partner candidate. This proposal includes specific actions that the new business partner candidate should take, their effects, and the services we provide to support those actions.

[1428] The process flow of each embodiment will be described below.

[1429] "Example 1"

[1430] Step 1: The AI ​​creates a list of companies in the country, including attributes such as the company's industry, size, and region.

[1431] Step 2: The AI ​​creates a list of companies that have similar attributes to good customers. This list is created by selecting companies that have similar attributes to good customers from the company list.

[1432] Step 3: The AI ​​compares the customer with a good customer and simulates what proposals would improve the customer's performance. This simulation is based on past transaction history, market trends, etc.

[1433] Step 4: The AI ​​generates a proposal based on the results of the simulation. This proposal includes the specific proposal content, its rationale, and the expected effects.

[1434] "Example 2"

[1435] Step 1: If the best customer is a large company in the IT industry, the AI ​​will list small and medium-sized companies in the same industry as potential new business partners.

[1436] Step 2: Based on what proposals good customers have received in the past that have improved their performance, the AI ​​simulates whether a similar proposal would lead to improved performance for a potential new business partner.

[1437] Step 3: Based on the results of the simulation, the AI ​​generates a proposal for the potential new business partner. This proposal describes the specific actions that the potential new business partner should take, their effects, and the services we provide to support those actions.

[1438] Example 1

[1439] Next, a description will be given of Example 1 of the embodiment 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[1440] In conventional systems for developing new business partners, creating company lists, listing companies with similar attributes to good customers, simulating proposal content, and generating proposal documents are often done manually, which can be problematic in terms of efficiency. In addition, the accuracy and effectiveness of the proposal content is uncertain, and it may not lead to an improvement in customer performance. This has created a demand for more efficient sales activities and more effective proposals.

[1441] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1442] In this invention, the server includes a means for creating a list of companies in Japan, a means for listing companies with similar attributes to good customers and using AI to recommend them, a means for comparing with good customers and using AI to simulate what proposals would improve customer performance, a means for AI to generate proposal guidelines and proposals based on the simulation results, and a means for generating proposals in natural language using a generative AI model. This makes it possible to efficiently develop new business partners and generate effective proposal content.

[1443] A "domestic company list" is a list that compiles information on companies located in Japan, including attributes such as the company's industry, size, and region.

[1444] A "good customer" is a customer with a good track record of transactions and excellent performance in the past, and is an important business partner for a company.

[1445] "Attributes" is information that indicates characteristics of a company, such as its industry, size, and region.

[1446] "AI recommendation" means using artificial intelligence to recommend the most suitable companies or proposals based on specific conditions.

[1447] "Simulation" is the process of predicting results under specific conditions based on past data and market trends.

[1448] The "proposal policy" indicates the basic direction and strategy of proposals to be made to customers.

[1449] A "proposal" is a document that describes the specific proposal to be made to a customer, its reasons, expected effects, etc.

[1450] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to generate sentences based on input prompts.

[1451] "Generating in natural language" means using artificial intelligence to create sentences in natural language that humans can understand.

[1452] This invention relates to a system for developing new business partners using AI. This system creates a list of companies in Japan, and from that list, lists companies that have similar attributes to good customers. It then simulates what proposals should be made to the listed companies to improve their customer performance, and generates proposals based on the results.

[1453] The server first retrieves company information from a domestic company database. This database contains attributes such as company industry, size, and region. The server uses SQL queries to extract the necessary data and create a company list. The server then uses an AI model to list companies that have similar attributes to good customers. Data analysis libraries such as scikit-learn and Pandas are used for this analysis. The server performs clustering based on company attributes such as industry, size, and region.

[1454] The server compares the listed companies with good customers and simulates what proposals would improve customer performance. This simulation is based on data such as past transaction history and market trends, and the AI ​​model makes predictions. Specifically, it performs regression analysis and clustering using past data.

[1455] Finally, the server generates a proposal policy and a proposal document based on the simulation results. The proposal document includes the specific proposal content, its rationale, expected effects, etc. Natural language processing (NLP) technology is used to generate the proposal document, utilizing a generative AI model.

[1456] A user instructs the system to create a list of new business partners, for example by inputting the following prompt into the generative AI model:

[1457] "Create a list of companies in your country that have similar attributes to your best customers. Then, run a simulation to see what proposals you could make to these companies to improve their performance, and generate proposals based on the results."

[1458] As a concrete example, a user instructs the system to "make a list of IT companies in Tokyo with more than 100 employees and make proposals for improving performance based on past transaction history." The server creates a list of companies based on the specified conditions and performs analysis and simulations using an AI model. Finally, a proposal is generated and provided to the user.

[1459] In this way, a system is realized in which the server, terminals, and users work together to efficiently develop new business partners.

[1460] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1461] Step 1: Create a list of companies

[1462] The server retrieves company information from a national company database. As input, a database containing company attributes such as industry, size, and region is used. The server uses SQL queries to extract the required data and create a company list. As output, a company list is generated.

[1463] Specific behavior:

[1464] The server executes a SQL query against the database:

[1465] sql SELECT FROM companies WHERE region = 'Japan';

[1466] This query retrieves company information for Japan.

[1467] Step 2: List companies with similar attributes to your best customers

[1468] The server uses an AI model to create a list of companies that have similar attributes to good customers. The list of companies and attribute information of good customers are used as input. The server performs clustering based on attributes such as the company's industry, size, and region. The list of companies is generated as output.

[1469] Specific behavior:

[1470] The server executes the following Python code to perform clustering.

[1471] python from sklearn.cluster import KMeans import pandas as pd Importing company data data = pd.read_csv('companies.csv') Running clustering kmeans = KMeans(n_clusters=5) clusters = kmeans.fit_predict(data[['industry', 'size', 'region']])

[1472] This code allows companies to be classified into clusters.

[1473] Step 3: Simulate the proposal

[1474] The server compares the listed companies with good customers and simulates what proposals would improve customer performance. As input, the server uses information on the listed companies, past transaction history, market trends, and other data. The server runs the simulation using regression analysis and predictive models. As output, it generates proposals.

[1475] Specific behavior:

[1476] The server runs the following Python code to perform the simulation:

[1477] python from sklearn.linear_model import LinearRegression Loading historical transaction data transaction_data = pd.read_csv('transactions.csv') Performing regression analysis model = LinearRegression() model.fit(transaction_data[['feature1', 'feature2']], transaction_data['performance']) Running a prediction predictions = model.predict(new_company_data[['feature1', 'feature2']])

[1478] This code predicts what proposals will be made to new business partners.

[1479] Step 4: Generate a proposal

[1480] The server generates a proposal policy and a proposal based on the simulation results. The simulation results are used as input. The server generates the proposal in natural language using a generative AI model. As output, a proposal is generated.

[1481] Specific behavior:

[1482] The server inputs the following prompt sentence into the generative AI model:

[1483] python prompt = """ Please prepare a proposal for a new business partner. Based on the information below, please include the specific proposal content, its justification, and the expected effects. Industry: IT Size: Medium Region: Tokyo Past transaction history: Yes Market trends: Growing """ response = gpt3.generate(prompt)

[1484] This code will generate a proposal.

[1485] Step 5: Submit your proposal

[1486] The user receives the generated proposal and makes a proposal to the new trading partner. As input, the generated proposal is used. As output, the proposal is provided to the new trading partner.

[1487] Specific behavior:

[1488] The user downloads the proposal generated from the system and submits it to the new business partner.

[1489] (Application example 1)

[1490] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[1491] Conventional systems for developing new business partners have difficulty efficiently listing companies with similar attributes to good customers and making appropriate proposals. In addition, generating proposal content requires a lot of manual work, which is time-consuming and labor-intensive. Furthermore, the system is not user-friendly because it does not take into account use on mobile devices such as smartphones and tablets. To solve these problems, a more efficient and effective system for developing new business partners is needed.

[1492] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1493] In this invention, the server includes a means for creating a list of companies in Japan, a means for listing companies with attributes similar to those of good customers and making recommendations using AI, a means for comparing with good customers and simulating what proposals would improve customer performance, a means for generating a proposal policy and a proposal document using AI, a means for simulating proposal contents for new business partners, a means for automatically generating a proposal document using a generation AI model, and a means including an application to be installed on a smartphone or tablet. This makes it possible to efficiently and effectively develop new business partners and quickly generate proposal contents.

[1494] The "domestic company list" is a list that collects basic information about companies located in the country and stores it in a database.

[1495] A "good customer" is a customer who is deemed to be of particularly high transaction value based on past transaction history and business performance.

[1496] "Attribute companies" are companies that have specific attributes such as industry, size, or region.

[1497] "AI recommendation means" is a function that uses artificial intelligence to recommend companies based on specific conditions.

[1498] A "means of simulation" is a function that predicts future results based on past data and market trends.

[1499] The "proposal policy" indicates the basic direction and strategy of the proposal content.

[1500] A "proposal" is a document that describes the specific proposal content, its reasons, and the expected effects.

[1501] A "new business partner" is a new business partner with whom we have not had any transactions until now.

[1502] A "generative AI model" is a model that is trained using artificial intelligence to perform a specific task.

[1503] A "prompt sentence" is an instruction sentence input to a generative AI model.

[1504] An "application installed on a smartphone or tablet" is software that runs on a mobile device.

[1505] A system for implementing the present invention uses a server, a mobile device such as a smartphone or tablet, and a generative AI model. The specific configuration and operation of the system are described below.

[1506] System Configuration

[1507] 1. Server

[1508] The server creates a list of companies in Japan and stores it in a database. The server also runs an AI model to analyze the attributes of good customers and list companies with similar attributes. In addition, the server simulates proposals to new clients and automatically generates proposals using a generative AI model.

[1509] 2. Mobile Devices

[1510] An application that communicates with the server is installed on a mobile device such as a smartphone or tablet, and provides an interface for the user to view a list of potential business partners and to view proposals.

[1511] Data processing and calculation

[1512] 1. Creating a list of companies

[1513] The server collects information on companies in Japan and creates a database that includes attributes such as industry, size, and region. This data is managed using Pandas.

[1514] 2. Analysis of loyal customer attributes

[1515] The server analyzes the data of good customers using KMeans clustering and classifies them into specific clusters, which makes it possible to identify companies that have similar attributes to good customers.

[1516] 3. Listing new business partners

[1517] The server filters companies that have similar attributes to its best customers and creates a list of new business partners, which is then provided to the user through an application on their mobile device.

[1518] 4. Proposed Simulation

[1519] The server uses RandomForestRegressor to simulate proposals for new trading partners. This simulation is based on past trading history and market trends.

[1520] 5. Proposal Generation

[1521] The server uses the generative AI model to automatically generate a proposal. This proposal includes the specific proposal content, its rationale, and the expected effects. The generative AI model uses the OpenAI API.

[1522] Examples

[1523] For example, for manufacturing company A, we generate the following prompt:

[1524] Company name: Company A

[1525] Industry: Manufacturing

[1526] Scale: 100

[1527] Region: Tokyo

[1528] Generate a proposal.

[1529] When this prompt sentence is input into the generative AI model, the AI ​​generates a specific proposal. For example, it may return a proposal such as, "The introduction of a new manufacturing line is expected to improve efficiency by 20%." In this way, users can make effective proposals to new business partners.

[1530] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1531] Step 1:

[1532] The server collects company information in the country and creates a database with attributes such as industry, size, region, etc. As input, it requires a data source of company information (e.g., a public company database) and as output, it obtains a list of companies in the form of a Pandas data frame. This data is used for subsequent analysis.

[1533] Step 2:

[1534] The server analyzes the data of good customers using KMeans clustering and classifies them into specific clusters. As input, it requires data of good customers (e.g. past transaction history, performance data), and as output, it obtains data of good customers with cluster labels. These cluster labels are used to identify the attributes of good customers.

[1535] Step 3:

[1536] The server filters companies with similar attributes to good customers and creates a list of new business partners. As input, it requires data of good customers with cluster labels and a list of companies in the country, and as output, it obtains a list of new business partners. This list is provided to the user through an application on the mobile device.

[1537] Step 4:

[1538] The server uses RandomForestRegressor to simulate proposals for new trading partners. As input, it requires a list of new trading partners and data on past trading history and market trends. As output, it obtains predictions of proposal contents. These predictions are used to generate proposal documents.

[1539] Step 5:

[1540] The server uses the generative AI model to automatically generate proposals. The inputs required are the predicted results of the proposal content and basic information about the new business partner (e.g. company name, industry, size, region), and the output is a proposal that includes the specific proposal content, its justification, and the expected effects. The generative AI model uses the OpenAI API.

[1541] Step 6:

[1542] A user views a list of new business partners and proposals through an application installed on a smartphone or tablet. As input, a list of new business partners and proposals provided by a server are required, and as output, they are displayed in a format that can be viewed by the user. This application provides an interface for the user to make effective proposals to new business partners.

[1543] Example 2

[1544] Next, a second embodiment of the second embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[1545] With the conventional system, it was difficult to make specific proposals to potential new business partners based on the success stories of good customers. In addition, it took a lot of time and effort to generate proposals, which made it difficult to conduct efficient sales activities.

[1546] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for creating a list of domestic companies, a means for listing companies with the same attributes as good customers and making recommendations using artificial intelligence, a means for comparing with good customers and simulating using artificial intelligence what proposals would improve customer performance, a means for generating a proposal based on the simulation results, and a means for providing the generated proposal to the user. This makes it possible to efficiently make specific proposals based on the success stories of good customers.

[1547] The "Domestic Company List" is a list that compiles information on companies located in Japan.

[1548] A "good customer" is a customer who has a good track record of transactions in the past and who can be expected to continue doing business with the company.

[1549] "Attribute companies" are companies that share a particular industry, size, or other common characteristics.

[1550] "Artificial intelligence" is a technology that enables computer systems to imitate human intelligence to learn and make inferences.

[1551] A "recommendation" is the suggestion of the best option based on specific criteria.

[1552] "Simulation" refers to the virtual reproduction of a real-world situation and predicting its outcomes.

[1553] A "proposal" is a document that documents a specific proposal and indicates specific actions to a business partner.

[1554] A "user" is someone who uses this system to create proposals and make them to business partners.

[1555] The present invention is a system for efficiently making specific proposals to potential new business partners based on success stories of good customers. A specific embodiment of this system will be described below.

[1556] The server first creates a list of companies in the country. To do this, a database management system (e.g., MySQL) is used to collect information on companies located in the country. Next, data on good customers is collected and past transaction records and performance data are analyzed. This analysis is performed using Python's Pandas library and NumPy library.

[1557] The server refers to an industry database to list companies with similar attributes to good customers. This allows small and medium-sized enterprises in the same industry to be extracted as potential new business partners. The extracted company list is recommended using artificial intelligence (e.g., generative AI model).

[1558] Next, the server simulates whether a proposal for a potential new business partner will lead to improved business performance based on the success stories of good customers. This simulation uses a generative AI model (e.g. GPT-4). Specific examples of prompt sentences include the following:

[1559] "Our good customer A has improved its performance in the past after receiving the following proposal. Please simulate what kind of effect you can expect if we make a similar proposal to a potential new business partner B."

[1560] Based on the simulation results, the server generates a proposal for the potential new business partner. This proposal describes the specific actions that the potential new business partner should take, their effects, and the services to support those actions. The generative AI model is used again to generate the proposal. Examples of specific prompt sentences include the following:

[1561] "Please prepare a proposal for potential new business partner B. In the proposal, please describe the specific actions that B should take, their effects, and the services we can provide to support those actions."

[1562] The generated proposal is provided to the user via the terminal. The user can make specific proposals to potential new business partners based on this proposal. This makes it possible to efficiently make specific proposals based on the success stories of good customers.

[1563] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1564] Step 1: Data collection

[1565] The server collects company information using a database management system (e.g., MySQL) to create a list of companies in Japan. As input, it obtains basic information about the companies (e.g., company name, location, industry, and size). As output, it generates a list of companies in Japan. Specifically, the server executes SQL queries to extract the required information from the database.

[1566] Step 2: Analyze your loyal customer data

[1567] The server collects and analyzes past transaction data and performance data of good customers. As input, it obtains transaction history and performance data of good customers. As output, it identifies successful proposals and factors that improved performance. Specifically, the server uses Python's Pandas library to analyze the data and extract success stories.

[1568] Step 3: List potential new business partners

[1569] The server refers to an industry database to list companies that have similar attributes as good customers. As input, it retrieves company information from the industry database. As output, it generates a list of potential new business partners. Specifically, the server executes an SQL query to extract companies that match the criteria.

[1570] Step 4: Simulation

[1571] The server simulates whether proposals for potential new business partners will lead to improved business performance, based on success stories of good customers. As input, it inputs the success stories of good customers and information on potential new business partners into the generative AI model. As output, it obtains the simulation results. In concrete terms, the server inputs the following prompt sentence into the generative AI model (e.g. GPT-4):

[1572] "Our good customer A has improved its performance in the past after receiving the following proposal. Please simulate what kind of effect you can expect if we make a similar proposal to a potential new business partner B."

[1573] Step 5: Generate a proposal

[1574] The server generates a proposal for a potential new business partner based on the simulation results. As input, it inputs the simulation results and information on the potential new business partner into the generative AI model. As output, a proposal is generated. Specifically, the server inputs the following prompt sentence into the generative AI model:

[1575] "Please prepare a proposal for potential new business partner B. In the proposal, please describe the specific actions that B should take, their effects, and the services we can provide to support those actions."

[1576] Step 6: Submit your proposal

[1577] The server sends the generated proposal to the terminal. As input, the server obtains the generated proposal. As output, the proposal is provided to the user. As a specific operation, the server sends the proposal to the terminal, and the terminal displays the proposal so that the user can confirm it. The user can make a specific proposal to a potential new business partner based on this proposal.

[1578] (Application example 2)

[1579] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[1580] With conventional systems, it was difficult to make effective proposals to potential new business partners based on the success stories of good customers. In addition, there was a problem that efficient sales activities could not be carried out because it took a lot of time and effort to generate proposals. Furthermore, the content of the proposals sometimes lacked consistency, which could reduce the trust of potential new business partners. In order to solve these issues, there is a need for a system that can generate prompt sentences based on the success stories of good customers and automatically generate effective proposals using AI.

[1581] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1582] In this invention, the server includes a means for creating a list of companies in Japan, a means for listing companies with attributes similar to those of good customers and making recommendations using AI, a means for comparing with good customers and simulating what proposals would improve customer performance, a means for AI to generate a proposal policy and a proposal, a means for generating a prompt sentence based on success stories of good customers, a means for generating a proposal based on the generated prompt sentence, and a means for outputting a proposal for a new business partner candidate. This makes it possible to automatically generate effective proposals based on success stories of good customers quickly and consistently.

[1583] A "means for creating a domestic company list" is a method or device for collecting information on companies existing in the country and organizing it in list form.

[1584] "Means for compiling a list of companies with similar attributes to good customers and recommending them using AI" refers to a method or device for identifying companies that have similar characteristics to good customers and recommending these companies using artificial intelligence.

[1585] "A means of using AI to simulate what proposals will improve customer performance by comparing with good customers" refers to a method or device that compares data on good customers with data on potential new business partners and uses artificial intelligence to predict what kind of proposals will contribute to improving performance.

[1586] "Means for AI-generated proposal guidelines and written proposals" refers to methods or devices for automatically creating proposal guidelines and specific written proposals using artificial intelligence.

[1587] A "means for generating prompt sentences based on success stories of good customers" refers to a method or device for creating instruction sentences (prompt sentences) for artificial intelligence based on past success stories of good customers.

[1588] The "means for generating a proposal based on the generated prompt sentence" refers to a method or device for an artificial intelligence to automatically create a proposal using the generated prompt sentence as input.

[1589] The "means for outputting a proposal to a new supplier candidate" refe...

Claims

1. A means of creating a list of companies in the country; A means for listing attribute companies having attributes similar to those of good customers from the company list and recommending them using a generating AI model; A means for simulating a proposal and an improvement in customer performance due to the proposal by comparing past data of the good customers and the attribute companies using the generative AI model; A means for generating a proposal plan and a proposal document based on the results of the simulation using the generating AI model; A system including:

2. The system of claim 1 , wherein the proposed policies and proposals generated by the generative AI model are intended to develop new business with the attribute companies that have similar attributes to the good customers.

3. The system of claim 1 , wherein the proposed policies and proposals generated by the generative AI model are aimed at improving the performance of the attributed companies that have similar attributes to the good customers.

Images